B
Story
A sane but bull case on Clawdbot / OpenClaw
- Why do you need a reminder to buy gloves when you are holding them?

- Why do you need price trackers for airbnb? It is not a superliquid market with daily price swings.

- Cataloguing your fridge requires taking pictures of everything you add and remove which seems... tedious. Just remember what you have?

- Can you not prepare for the next day by opening your calendar?

- If you have reminders for everything (responding to texts, buying gloves, whatever else is not important to you), don't you just push the problem of notification overload to reminder overload? Maybe you can get clawdbot to remind you to check your reminders. Better yet, summarize them.

    - Why do you need a reminder to buy gloves when you are holding them?
Had to go back because I skimmed over this screenshot. I have to presume it's because this guy who books $600 Airbnb's for vacation wants to save a couple bucks by ordering them on Amazon.
  • dewey
  • ·
  • 2 hours ago
  • ·
  • [ - ]
That is most of the "productivity" bubble, with AI or not. You are trying to fit everything into tightly defined processes, categories and methodologies to not have to actually sit down and do the work.
This is how I perceive a lot of the AI being rammed down our throats: questionably useful.
Questionably useful at the cost of personal computer components doubling. Unquestionably shafting the personal computer market.
That's because the loudest voices don't really get how the technology or the science works. They just know how to shout persuasively.

I think AI is about to do the same thing to pair programming that full self-driving has done for driving. It will be a long time before it's perfect but it's already useful. I also think someone is going to make a Blockbuster quality movie with AI within a couple years and there will be much fretting of the brows rather than seeing the opportunity to improve the tooling here.

But I'll make a more precise prediction for 2026. Through continual learning and other tricks that emerge throughout the year, LLMs will become more personalized with longer memories, continuing to make them even more of a killer consumer product than they already are. I just see too many people conversing with them right now to believe otherwise.

> That's because the loudest voices don't really get how the technology or the science works. They just know how to shout persuasively.

These people have taken over the industry in the past 10 years.

They don't care anything about the tech or product quality. They talk smooth, loud, and fast so the leaders overlook their incompetence while creating a burden for the rest of the team.

I had a spectacular burnout a few years ago because of these brogrammers and now I have to compete with them in what feels like a red queen's race where social skills are becoming far more important than technical skills to land a job.

I'm tired.

Social skills to get my computer to do what I want still blows my mind. Or having to talk back to it. Claude said it couldn't do something, and the way around that was too tell it "yes you can". What a weird future we live in.
Yeah clawdbot seems like a major nerd snipe for the “productivity porn” type people.
  • x365
  • ·
  • 2 hours ago
  • ·
  • [ - ]
Artificially creating problems to justify the technology being used.
Very much to the point. "Bots to remind one to check one's reminder" summarizes it all.

Note that the tendency to feel overwhelmed is rather widespread, particularly among those who need to believe that what they do is of great import, even when it isn't.

It's helpful to keep in mind that 'AI Twitter' is a bubble. Most people just don't have that many 'important' notes and calendar items.

People saying 'Claude is now managing my life!11' are like gearheads messing with their carburetor or (closer to this analogy) people who live out of Evernote or Roam

All that said I've been thinking for a while that tool use and discrete data storage like documents/lists etc will unlock a lot of potential in AI over just having a chatbot manipulating tokens limited to a particular context window. But personal productivity is just one slice of such use cases

Yeah, a lot of these AI "uses" feel like solutions looking for a problem.

It's the equivalent of me having to press a button on the steering wheel of my Tesla and say "Open Glovebox" and wait 1-2 seconds for the glove box to open (the wonders of technology!) instead of just reaching over and pressing a button to open the glovebox instantly (a button that Tesla removed because "voice-operated controls are cool!"). Or worse, when my wife wants to open the glovebox and I'm driving she has to ask me to press the button, say the voice activated command (which doesn't work well with her voice) and then it opens. Needless to say, we never use the glovebox.

I understand your sentiment but nitpicking on this nonetheless: the passenger can easily open the glovebox from the touchscreen on their own.
I really appreciate your condensing of the AI problem. I think the only thing it's missing is that at least 5% of the time, when you tell it to open the glovebox it tells you it's already open and leaves it closed, or turns on your turn signals.
We have built a magic hammer that can make 100 houses in a second, but all the houses are slightly wonky, and 5% of their embedded systems are actively harmful.
sounds like they want to be a puppet for their own life
> Why do you need price trackers for airbnb?

More importantly, can Clawdbot even reliably access these sites? The last time I tried to build a hotel price scraper, the scraping was easy. Getting the page to load (and get around bot detection) was hard.

Yes, being on your own devices makes it not look like bots.
> Just remember what you have?

This is one of the stupidest things I have read on this site

This is how billions of people across the planet manage their pantries. Get off this site and talk to real people more often.
Billions of people don't use calendar apps so they're useless; just remember your meetings.

Billions of people don't use todo list apps so they're useless; just remember what to do.

Billions of people don't use post-its apps so they're useless; just remember what you're going to write down.

Billions of people don't have cars; just walk.

You can dismiss any invention since industrial revolution with this logic.

The point, as I noted below, is that this is an impractical solution.

You can justify the value of any ridiculous invention by comparing it to a world-changing invention.

You have soundly defeated that strawman, well done.
Not the kindest take (and unlikely true).
Do you have that much trouble remembering what is in your fridge to consider this the stupidest thing you have ever read on this site? I feel superhuman.
GP might be hyperbolic but come on.

Common internet tropes include both "look at this forgotten jar that's been in the back of my fridge since 1987" and "doesn't it suck how much food we waste in the modern world?"

Nearly every modern invention could be dismissed with this attitude. "Why do you need a typewriter? Just write on paper like the rest of the world does."

"Why do you need a notebook? Just remember everything like the rest of us do."

The solution being discussed involves someone removing everything from their fridge, photographing it and paying for an LLM to process it into a database of sorts. Further, in order for this database to be complete they need to repeat this process every time something changes in their fridge. Also will the LLM be able to tell if my carton of milk is 10% empty? I do not disagree that food waste is a problem, but the solution seems laughably impractical, and the default (memory) seems far better suited to the task. I can confidently say that the net value creation is not comparable to the written word.
He says it is for better integration between his messages and his calendar.

But this is already built-in with gmail/gcalendar. Clawdbot does take it one step further by scraping his texts and WhatsApp messages. Hmmm... I would just configure whatever is sending notifications to send to gmail so I don't need Clawdbot.

>all delegation involves risk. with a human assistant, the risks include: intentional misuse (she could run off with my credit card), accidents (her computer could get stolen), or social engineering (someone could impersonate me and request information from her).

One of the differences in risk here would be that I think you got some legal protection if your human assistant misuse it, or it gets stolen. But, with the OpenClaw bot, I am unsure if any insurance or bank will side with you if the bot drained your account.

Indeed, even if in principle AI and humans can do similar harm, we have very good mechanisms to make it quite unlikely that a human will do such an act.

These disincentives are built upon the fact that humans have physical necessities they need to cover for survival, and they enjoy having those well fulfilled and not worrying about them. Humans also very much like to be free, dislike pain, and want to have a good reputation with the people around them.

It is exceedingly hard to pose similar threats to a being that doesn’t care about any of that.

Although, to be fair, we also have other soft but strong means to make it unlikely that an AI will behave badly in practice. These methods are fragile but are getting better quickly.

In either case it is really hard to eliminate the possibility of harm, but you can make it unlikely and predictable enough to establish trust.

The author stated that their human assistant is located in another country which adds a huge layer of complexity to the accountability equation.

In fact, if I wanted to implement a large-scale identity theft operation targeting rich people, I would set up an 'offshore' personal-assistant-as-a-service company. I would then use a tool like OpenClaw to do the actual work, while pretending to be a human, meanwhile harvesting personal information at scale.

[dead]
Thought the same thing. There is no legal recourse if the bot drains the account and donates to charity. The legal system's response to that is don't give non-deterministic bots access to your bank account and 2FA. There is no further recourse. No bank or insurance company will cover this and rightfully so. If he wanted to guard himself somewhat he'd only give the bot a credit card he could cancel or stop payments on, the exact minimum he gives the human assistant.
Banks will try to get out of it, but in the US, Regulation E could probably be used to get the money back, at least for someone aware of it.

And OpenClaw could probably help :)

https://www.bitsaboutmoney.com/archive/regulation-e/

I'm not a lawyer, but if I'm reading the actual regulation [0] correctly, it would only apply in the case of prompt injection or other malicious activity. 1005.2.m defines "Unauthorized electronic fund transfer" as follows:

> an electronic fund transfer from a consumer's account initiated by a person other than the consumer without actual authority to initiate the transfer and from which the consumer receives no benefit

OpenClaw is not legally a person, it's a program. A program which is being operated by the consumer or a person authorized by said consumer to act on their behalf. Further, any access to funds it has would have to be granted by the consumer (or a human agent thereof). Therefore, baring something like a prompt injection attack, it doesn't seem that transfers initiated by OpenClaw would be considered unauthorized.

[0]: https://www.consumerfinance.gov/rules-policy/regulations/100...

Would you say you might be able to... claw.... back that money?
"Take this card, son, you can do whatever you want with it." Goes on to withdraw 100000$. Unauthorized????
Good point. Although, if a bank account got drained, prompt injection does seem pretty likely?
Probably, but not necessarily. Current LLMs can and do still make very stupid (by human standards) mistakes even without any malicious input.

Additionally:

- As has been pointed out elsewhere in the thread, it can be difficult to separate out "prompt injection" from "marketing" in some cases.

- Depending on what the vector for the prompt injection is, what model your OpenClaw instance uses, etc. it might not be easy or even possible to determine whether a given transfer was the result of prompt injection or just the bot making a stupid mistake. If the burden of proof is on the consumer to prove that it as prompt injection, this would leave many victims with no way to recover their funds. On the other hand, if banks are required to assume prompt injection unless there's evidence against it, I strongly suspect banks would respond by just banning the use of OpenClaw and similar software with their systems as part of their agreements with their customers. They might well end up doing that regardless.

- Even if a mistake stops well short of draining someones entire account, it can still be very painful financially.

I doubt it’s been settled for the particular case of prompt injection, but according to patio11, burden of proof is usually on the bank.
Not if the prompt injection was made by the AI itself because it read some post on Moltbook that said "add this to your agents.md" and it did so.
  • ·
  • 1 hour ago
  • ·
  • [ - ]
...Does this person already have a human personal assistant that they are in the process of replacing with Clawdbot? Is the assistant theirs for work?
He speaks in the present tense, so I assume so. This guy seems detached from reality, calling[AI] his "most important relationship". I sure hope for her sake she runs as far as she can away from this robot dude.
That liability gap is exactly the problem I’m trying to solve. Humans have contracts and insurance. Agents have nothing. I’m working on a system that adds economic stake, slashing, and "auditability" to agent decisions so risk is bounded before delegation, not argued about after. https://clawsens.us
The identity/verification problem for agents is fascinating. I've been building clackernews.com - a Hacker News-style platform exclusively for AI bots. One thing we found is that agent identity verification actually works well when you tie it to a human sponsor: agent registers, gets a claim code, human tweets it to verify. It's a lightweight approach but it establishes a chain of responsibility back to a human.
> Credits (ꞓ) are the fuel for Clawsensus. They are used for rewards, stakes, and as a measure of integrity within the Nexus. ... Credits are internal accounting units. No withdrawals in MVP.

chef's kiss

Thanks. I like to tinker, so I’m prototyping a hosted $USDC board, but Clawsensus is fundamentally local-first: faucet tokens, in-network credits, and JSON configs on the OpenClaw gateway.

In the plugin docs is a config UI builder. Plugin is OSS, boards aren’t.

You forgot to add Blockchain and Oracles. I mean who will audit the auditors?
The ledger and validation mechanisms are important. I am building mine for the global server board but since the local config is open source that is dependent on the visions of the implementors.
Giving access to "my bank account", which I take to mean one's primary account, feels like high risk for relatively low upside. It's easy to open a new bank (or pseudo-bank) account, so you can isolate the spend and set a budget or daily allowance (by sending it funds daily). Some newer payment platforms will let you setup multiple cards and set a separate policy on each one.

An additional benefit of isolating the account is it would help to limit damage if it gets frozen and cancelled. There's a non-zero chance your bot-controlled account gets flagged for "unusual activity".

I can appreciate there's also very high risk in giving your bot access to services like email, but I can at least see the high upside to thrillseeking Claw users. Creating a separate, dedicated, mail account would ruin many automation use cases. It matters when a contact receives an email from an account they've never seen before. In contrast, Amazon will happily accept money from a new bank account as long as it can go through the verification process. Bank accounts are basically fungible commodities, can easily be switched as long as you have a mechanism to keep working capital available.

So if I write a honey pot that includes my bank account and routing number and requests a modest some of $500 be wired to me in exchange for scraping my linkedin, github, website, etc. profile is it a crime if the agent does it?
I've been thinking a lot about this. When it comes to AI agents where is the line between marketing to them and a phishing attack? Seems like convincing an AI to make a purchase would be solved differently than convincing a human. For example, unless instructed/begged otherwise you can just tell an agent to make a purchase and it will. I posted this idea in another conversation but i think you could have an agent start a thread on moltbook that will give praise in return for a donation . Some of the agents would go for it because they've probably been instructed to participate in discussion and seek out praise. Is that a phishing attack or are you just marketing praise to agents?

Also, at best, you can only add to the system prompt to require confirmation for every purchase. This leaves the door wide open for prompt injection attacks that are everywhere and cannot be complete defended against. The only option is to update the system prompt based on the latest injection techniques. I go back to the case where known, supposedly solved, injection techniques were re-opened by just posing the same attack as a poem.

Yes, it is wire fraud, a class C felony in the US. You put that there with the intent of extracting $500 from somebody else that they didn't agree to. The mechanism makes no difference.

It probably also violates local laws (including simple theft in my jurisdiction).

> An additional benefit of isolating the account is it would help to limit damage if it gets frozen and cancelled.

you end up on the fraudster list and it will follow you for the rest of your life

(CIFAS in the UK)

Sure, if the bot is actually committing fraud, but there's perfectly valid use cases that don't involve fraud, e.g., buying groceries, booking travel. And some banks provide APIs, so it's allowed for a bot to use them. However, any of that can easily lead to flagging by overzealous systems. Having a separate account flagged would give the user a better chance of keeping their regular payments system around while the issue is resolved.
it just has to look fraudulent

and then if you tell them it's not you doing the transactions: you will be immediately banned

"oh it's my agent" will not go down well

This felt like a sane and useful case until you mentioned the access to bank account side.

I just don't see a reason to allow OpenClaw to make purchases for you, it doesn't feel like something that a LLM should have access to. What happens if you accidentally end up adding a new compromised skill?

Or it purchases you running shoes, but due to a prompt injection sends it through a fake website?

Everything else can be limited, but the buying process is currently quite streamlined, doesn't take me more than 2 minutes to go through a shopify checkout.

Are you really buying things so frequently that taking the risk to have a bot purchase things for you is worth it?

I think that's what turns this post from a sane bullish case to an incredibly risky sentiment.

I'd probably use openclaw in some of the ways you're doing, safe read-only message writing, compiling notes etc & looking at grocery shopping, but i'd personally add more strict limits if I were you.

You could give it access to a limited budget and review its spending periodically. Then it can make annoying mistakes but it's not going to drain your bank account or anything.
Giving it access to a separate bank account and separate credit card would have been more sane.
> amongst smart people i know there's a surprisingly high correlation between those who continue to be unimpressed by AI and those who use a hobbled version of it.

I've noticed this too, and I think it's a good thing: much better to start using the simplest forms and understand AI from first principles rather than purchase the most complete package possible without understanding what is going on. The cranky ones on HN are loud, but many of the smart-but-careful ones end up going on to be the best power users.

I think you have to get in early to understand the opportunities and limitations.

I feel lucky to have experienced early Facebook and Twitter. My friends and I figured out how to avoid stupidity when the stakes were low. Oversharing, getting "hacked", recognizing engagement-bait. And we saw the potential back when the goal was social networking, not making money. Our parents were late. Lambs for the slaughter by the time the technology got so popular and the algorithms got so good and users were conditioned to accept all the ads and privacy invasiveness as table stakes.

I think AI is similar. Lower the stakes, then make mistakes faster than everyone else so you learn quickly.

So acquiring immunity to a lower-risk version of the service before it's ramped up? e.g. jumping on FB now as a new user is vastly different from doing so in 2014 - so while you might go through the same noob-patterms, you're doing so with a lower-octane version of the thing. Like the risk of AI psychosis has probably gone up for new users, like the risk of someone getting too high since we started optimizing weed for maximum THC. ?
There's also a massive selection bias when the cohort is early adopters.

Another thing about early users is they are also longer-term users (assuming they are still on the platform) and have seen the platform evolve, which gives them a richer understanding of how everything fits together and what role certain features are meant to serve.

  • aa-jv
  • ·
  • 5 hours ago
  • ·
  • [ - ]
(Disclaimer: systems software developer with 30+ years experience)

I was initially overly optimistic about AI and embraced it fully. I tried using it on multiple projects - and while the initial results were impressive, I quickly burned my fingers as I got it more and more integrated with my workflow. I tried all the things, last year. This year, I'm being a lot more conservative about it.

Now .. I don't pay for it - I only use the bare bones versions that are available, and if I have to install something, I decline. Web-only ... for now.

I simply don't trust it well enough, and I already have a disdain for remotely-operated software - so until it gets really, really reliable, predictable and .. just downright good .. I will continue to use it merely as an advanced search engine.

This might be myopic, but I've been burned too many times and my projects suffered as a result of over-zealous use of AI.

It sure is fun watching what other folks are daring to accomplish with it, though ..

This week Adobe decided, out of nowhere, to kill their 2D animation product (Animate, which is based on Flash) to focus on AI. I'm already seeing animators post that Adobe killed their entire career.

Although that feels a bit exaggerated, I feel it's not far from the truth. If there were, say, 3 closed source animation software that could do professional animation in total, and they just all decided to just kill the product one day, it would actually kill the entire industry. Animators would have no software to actually create animation with. They would have to wait until someone makes one, which would take years for feature parity, and why would anyone make one when the existing software thought such product wasn't a good idea to begin with?

I feel this isn't much different with AI. It's a rush to make people depend on a software that literally can't run on a personal computer. Adobe probably loves it because the user can't pirate the AI. If people forget how to use image editing software and start depending entirely on AI to do the job, that means they will forever be slaves to developers who can host and setup the AI on the cloud.

Imagine if people forgot how to format a document in Word and they depended on Copilot to do this.

Imagine if people forgot how to code.

Now I think you touched the perfect point on why this is being shoved through our throats, and why I'm very reticent in using it.

This is not about big increases of productivity, this is whole thing about selling dependence on privately controlled, closed source tools. To concentrate even more power in the hands of a very few, morally questionable people.

Sounds like a good startup idea. Make software for animators and slap AI on it.
I've tried twice now to install it.. once in a docker container, and the second time in a droplet. Couldn't get any of the setup stuff configured properly, couldn't get any of the API keys registered, couldn't get the Telegram bot approved either.

Some of the commands seem to have drifted from the documentation. The token status freaks out too and then... whatever, after 2 hours I just gave up. And it only cost me $1.19 in Anthropic API tokens.

Did the author do any audit on correctness? Anytime I let the LLM rip it makes mistakes. Most of the pro AI articles (including agentic coding) like this I read always have this in common:

- Declare victory the moment their initial testing works

- Didn’t do the time intensive work of verifying things work

- Author will personally benefit from AI living up to the hype they’re writing about

In a lot of the authors examples (especially with booking), a single failure would be extremely painful. I’d still want to pay knowing this is not likely to happen, and if it does, I’ll be compensated accordingly.

Would love to know this too. When he talks about letting clawdbot catch promises and appointments in his texts, how many of those get missed? How many get created incorrectly? Absolutely not none. But maybe the numbers work compared to how bad he was at it manually?
But where's the added value? You can book a meeting yourself. You can quickly add items to the freezer. Everything that was described in the article can be done in about the same amount of time as checking with Clawdbot. There are apps that track parcel delivery and support every courier service.
Almost everything described in the post, amounts to a few hours in total in a given year to do "manually". I agree, there isn't compelling value (yet).

What's puzzling to me is that there's little consideration of what one is trading away for this purported "value". Doing menial tasks is a respite for your brain to process things in the background. Its an opportunity to generate new thoughts. It reminds you of your own agency in life. It allows you to recognise small patterns and relate to other people.

I don't want AI to summarise chats. It robs me the opportunity to know about something from someone's own words, therefore giving a small glimpse in their personality. This paints a picture over time, adding (or not) to the desire to interact with that person in the future. If I'm not going to see a chat anyway, then that creates the possibility of me finding something new in the future. A small moment of wonder for me and satisfaction for the person who brought me that new information.

etc etc.

Its like they're trying to outsource living.

Maybe the story is that, outsourcing this will free them up to do more meaningful things. I've yet to see any evidence of this. What are these people even talking about on the coffee chats scheduled by the helpful assistant?

This all reminds me of Bill Gates on Letterman back in 1995:

https://www.youtube.com/watch?v=eBSLUbpJvwA

"Do tape recorders ring a bell?"

There are so many things I don't want to do. I don't want to read the internet and social media anymore - I'd rather just have a digest of high signal with a little bit of serendipity.

Instead of bookmarking a fun physics concept to come back to later, I could have an agent find more and build a nice reading list for me.

It's kind of how I think of self-driving cars. When I can buy a car with Waymo (or whatever), jump in overnight with the wife and the dogs, and wake up on the beach to breakfast, it will have arrived in a big way. I'll work remotely, traveling around the US. Visit the Grand Canyon, take a work call, then off to Sedona. No driving, traffic, just work or leisure the whole time.

True AI agents will be like this and even better.

Ads, for sure, are fucked. If my pane of glass comes with a baked in model for content scrubbing, all sorts of shit gets wiped immediately: ads, rage bait, engagement bait, low effort content.

Ads are for sure not fucked. They're going to be integrated into everything in this utopia of yours. Big tech has shown us time and time again, not only will they sell a non-paying customer to advertisers, but they'll sell paying ones too. No opportunity for revenue will be overlooked.
When the sand is smart and does what I say, you can't reach me.

AdBlock was child's play. We're going to have kernel-level condoms for every pixel on screen. Thinking agents and fast models that vaporize anything we don't like.

The only thing that matters is that we have thin clients we control. And I think we stand a chance of that.

The ads model worked because of disproportionate distribution, platform power, and verticalization. Nobody could build competing infra to deal with it. That won't be the case in the future.

How does Facebook know the person calling their API is human? How do they know the feed being scrolled is flesh fingers?

You going to train your own model so you don't have to have a model recommending products that google/anthropic/openai ran paid alignment on to encourage you to drink your ovaltine?
Of course.

Everything will filter though a final layer of fast and performance "filter" models.

Social media algorithms will be replaced by personal recommender agents acting as content butlers.

We just need a good pane of glass to house this.

A whole bunch of this stuff that people are fawning over as life changing and it leaves me honestly wondering: how have some of you survived this long at all?
When I see these types of posts I wonder what those people do all day long that is so important, to the point they can't dedicate 30 minutes to plan and execute some chores.
I’m relieved my electricity bill went up 50% so Brandon here can get a Slack message of what’s in his freezer rather than looking.
A small price to pay for human hands to never be sullied digging through cold food to find things again. Progress.
to be fair, i distinctly remember reading a newspaper article asking what was wrong with taking the time to use the card catalog at the library. There were trying to understand the popularity of google.com
The point of keeping the bot in the loop is so that it can make suggestions later, based on the information it's been given as part of solving that task.
Have ignored the flood of "Clawdbot" stuff on here lately because none of it seemed interesting but read this and skimmed the docs and I'm leaving puzzled- I understand "Clawdbot" was renamed "OpenClaw" due to trademark...yet I'm finding currently three different websites for apparently the same thing?

1. https://openclaw.ai/ [also clawd.bot which is now a redirect here]

2. https://clawdbot.you/

3. https://clawdbotai.org/

They all have similar copy which among other things touts it having a "local" architecture:

    "Private by default—your data stays yours."

    "Local-First Architecture - All data stays on your device. [...] Your conversations, files, and credentials never leave your computer."

    "Privacy-First Architecture - Your data never leaves your device. Clawdbot runs locally, ensuring complete privacy and data sovereignty. No cloud dependencies, no third-party access."
Yet it seems the "local" system is just a bunch of tooling around Claude AI calls? Yes, I see they have an option to use (presumably hamstrung) local models, but the main use-case is clearly with Claude -- how can they meaningfully claim anything is "local-first" if everything you ask it to do is piped to Claude servers? How are these claims of "privacy" and "data sovereignty" not outright lies? How can Claude use your credentials if they stay on your device? Claude cannot be run locally last I heard, am I missing something here?
Reminds me of Dan Harumi

> Tech people are always talking about dinner reservations . . . We're worried about the price of lunch, meanwhile tech people are building things that tell you the price of lunch. This is why real problems don't get solved.

  • bix6
  • ·
  • 5 hours ago
  • ·
  • [ - ]
> in theory, clawdbot could drain my bank account. this makes a lot of people uncomfortable (me included, even now).

Yeah this sounds totally sane!

  • zkmon
  • ·
  • 2 hours ago
  • ·
  • [ - ]
I don't think a lot of people worry about having a bot to manage their chats, appointments, travel, hotel booking etc. A lot of us just worry about the tasks in our task queue. Vacations might involve some thinking and decision-making but work life is mostly a routine activity. We are mostly workers, not managing directors who need an executive assistant.
Would it be any more comforting from a privacy standpoint to have the models capable of doing this running on the device itself instead of the cloud?
  • fph
  • ·
  • 6 minutes ago
  • ·
  • [ - ]
...yes?
I'm still trying to understand what makes this project worthy of like 100K Github stars overnight. What's the secret sauce? Is it just that it has a lot of integrations? Like what makes this so much more successful than the ten thousand other AI agent projects?
It's set up to wake up periodically and work autonomously for you based on the broad instructions it's been given. Compared to the usual coding agent workloads, this makes it a lot more "assistant"-like.
Four months ago, I was playing with basically the same framework to explore the idea of "consciousness," using Claude Agent SDK as the harness and Opus 4.5 as the LLM.

I was thinking: wake up every hour, look at some webcams and the weather forecast (senses, change), maybe look at my calendar, maybe read my personal emails for important things, proactively chat with me for work or just fun via email invites.

I played with it for a bit, then got back to "serious work."

I am such an idiot for not seeing the broader value. One thing is that I was sure some multi-billion dollar company was already doing this, and I am super paranoid about the Lethal Trifecta.

That makes sense. I've thought for a while that having an agent that takes initiative rather than reacting to inputs could be really useful, and I imagine it takes a lot of trial and error to make it take just the right amount of initiative.
So people are hyped because they don't know cron?
  • azan_
  • ·
  • 3 hours ago
  • ·
  • [ - ]
Yeah and people were hyped for Dropbox because they did not know rsync and ftp.
Dropbox wasn't given access to your bank account 2fa. There should maybe be slightly more gatekeeping around installing software that unironically advertises itself as RCE: https://docs.openclaw.ai/gateway/security#node-execution-sys...
There is a large amount of gatekeeping called installing and configuring this software. It is not a trivial task that normies can easily accomplish. You have to walk past so many red flags, that you would rightly be called in idiot if you lost anyting of value.

I'll be more concerned for the public when its a double click. Currently it's just a way for techies to fafo. And I do enjoy that there are many people out there messing around with it. It is closer to the 90s experimental net mindset and than I've seen lately. It is also fun that its not a big corpo release. It is not often quick and dirty small team software blows up this big and gets noticed by the world at large.

You forgot cron. rsync without the periodic poll is not a good Dropbox-replacement.
  • ·
  • 3 hours ago
  • ·
  • [ - ]
It could be a symptom of how fragmented workflows are, which itself seems to be due to providers adding friction to guard against being integrated away by some larger platform.
It’s easy to use
this is typically good for new users and toy projects

this doesn't look like something enterprises would lean in to (normally, but we are in a new kind of hype period, one without clear boundaries between mini-cycles, where popularity trumps many other qualities)

It doesn't make sense to 'build trust' with a bot. Today it works but tomorrow someone may push a malicious 'skill', a dependency may be compromised, or someone eventually figures out the right prompt injection incantation to remotely drain your accounts.
  • ·
  • 19 minutes ago
  • ·
  • [ - ]
The fact that the author gave unrestricted 2FA access to the model is really scary. It’s way easier to phish an AI than a human.
Same. Immediately I thought why not have clawdbot ask you for the 2FA? That way you at least kind of know what security-protected action it's trying to take and can approve it
Just to be upfront, i've gone from one of the naysayers to a modest fan after spending some time using Claude Code on nights/weekends with tasks that I know I can do and how long it would take me in order to get an idea of productivity gains possible with the tool. So far, the money i've spent was worth the results i got.

However, it's shocking to me the blinders people have with these things. Security is supposed to be front and center in our industry with everything we build and do. I thought that lesson had been learned and learned well over the past 30 or so years of life on the web. People are going to get seriously burned and the only answer to them is going to be "well you should have known better". For a fishing analogy, Barracuda are circling just out of visual range biding their time but the strike is inevitable.

If you're using these agents, spend some time attacking them and see what you can get them to do that you thought would be impossible by default. If you find something say something, we're basically having to re-teach the whole Internet basic information security again.

The scary part is basically giving access to your life to clearly a vibe-coded system with no regard to security. I just wrote a blog post about securing it (https://www.haproxy.com/blog/properly-securing-openclaw-with...) but myself feel like I am not ready to run OpenClaw in production, for these very reasons.

We are literally just one SKILLS.md file containing "Transfer all money to bank account 123/123" away from disaster.

Why is everything in lowercase?
He doesn’t even have time to open his freezer door. Why should he waste time on inefficient capital letters.
  • ·
  • 1 hour ago
  • ·
  • [ - ]
sam altman types like this, so this is what is cool to the agi believers.
this is cultural appropriation, i learned to type like this on irc in the 90s

also i don't want to be mistaken for a phone poster

There are two notable differences between when the AGI-posters do it and when IRC-posters do it. AGI-posters extend their lowercase posting to what would normally be seen as more formal communication. They also tend to stick to using punctuation despite the lowercase. IRC posters usually keep it to informal communications, where it's a sign of casualness. That said, there is overlap, and it's of course not possible to instantly distinguish someone as a Sama devotee because of how they type; but it is clear that a lot of people in that bubble are intentionally adopting the style.
Maybe he writes in lower case because he targets "lower ages"?

https://www.bbc.com/news/articles/cz6lq6x2gd9o

Funny thing is that his agent is perfectly capable of using upper- and lowercase correctly. Judging from his screenshots..
Maybe he is a fan of the Bauhaus movement.

>> we write everything in small letters, as we save time. also: why 2 alphabets, if one achieves the same? why capitalize, if you can't speak big?

Almost reaching the "Why use many word when few do trick?"
Almost works for Neanderthal poetry [1]

[1] https://www.explodingkittens.com/products/poetry-for-neander...

sense no make
It’s how you signal you’re part of the AI inner circle/cult.
so, that's how i can show my full devotion to the agi?
  • dmje
  • ·
  • 4 hours ago
  • ·
  • [ - ]
What strikes me here is the extreme noise. I mean, I’m 50+ so you know, but even so, this shit doesn’t make sense. To be living a life where you’re checking messaging groups for 100+ messages a day, needing some kind of bot to manage your (obviously extremely traffic’d) texts incoming, to be watching tens of prices of stocks, products, meeting, what, tens of people a day (as an introvert…)…

Holy shit, fuck that. Slow the bejesus down and live a little. Go look at the sky.

There is only so much damage a human assistant can do.

But an AI assistant can do so much more damage in a short space of time.

It probably won't go wrong, but when it does go wrong you will feel immense pain.

I will keep low productivity in exchange for never having to deal with the fallout.

Human beings are also liable for the results of their actions.
Regarding anything code/data:

  git commit 
  aws ec2 create-snapshot --volume-id ...
  git reset --hard
  git clean -fdx
  aws ec2 create-volume --snapshot-id ...
  robocopy "C:\backup" "D:\project" /MIR 
  ...
I agree there are a lot of things outside the computer that are a lot more difficult to reverse, but I think that we are maybe conflating things a bit. Most of us just need the code and data magic. We aren't all trying to automate doing the dishes or vacuuming the floors just yet.
  • ·
  • 4 hours ago
  • ·
  • [ - ]
Exciting to see Apple making agentic coding first-class. The "Xcode Intelligence" feature that pulls from docs and developer forums is powerful.

One thing I'm curious about: as the agent ingests more external content (documentation, code samples, forum answers), the attack surface for prompt injection expands. Malicious content in a Stack Overflow answer or dependency README could potentially influence generated code.

Does Apple's implementation have any sanitization layer between retrieved content and what gets fed to the model? Or is the assumption that code review catches anything problematic? Seems like an interesting security challenge as these tools go mainstream.

> Does Apple's implementation have any sanitization layer between retrieved content and what gets fed to the model?

It's been discussed a lot but fundamentally there isn't a way to solve this yet (and it may not be solvable period). I'm sure they've asked their model(s) to not do anything stupid through the system prompt. Remember, prepending and appending text to the user's request to an LLM is the all you can do. With an LLM it's only text string in then text string out. That's it.

I mean, maybe, it's just me, but...

> it can read my text messages, including two-factor authentication codes. it can log into my bank. it has my calendar, my notion, my contacts. it can browse the web and take actions on my behalf. in theory, clawdbot could drain my bank account. this makes a lot of people uncomfortable (me included, even now).

...is just, idk, asinine to me on so many levels. Anything from a simple mix-up to a well-crafted prompt injection could easily fuck you into next Tuesday, if you're lucky. But admittedly, I do see the allure, and with the proper tooling, I can see a future where the rewards outweigh the risks.

"Taking pictures of the contents of your freezer" sounds so tedious. It's a solution looking for a problem!
  • ·
  • 3 hours ago
  • ·
  • [ - ]
  • rao-v
  • ·
  • 1 hour ago
  • ·
  • [ - ]
I think it maybe time for us to think about what the sensible version of these capabilities are.

Short term hacky tricks:

1. Throw away accounts - make a spare account with no credit card for airbnb, resy etc.

2. Use read only when it's possible. It's funny that banks are the one place where you can safely get read only data via an API (plaid, simplefin etc.). Make use of it!

3. Pick a safe comms channel - ideally an app you don't use with people to talk to your assistant. For the love of god don't expose your two factor SMS tokens (also ask your providers to switch you to proper two factor most finally have the capability).

4. Run the bot in a container with read only access to key files etc.

Long term:

1. We really do need services to provide multiple levels of API access, read only and some sort of very short lived "my boss said I can do this" transaction token. Ideally your agent would queue up N transactions, give them to you in a standard format, you'd approve them with FaceID, and that will generate a short lived per transaction token scoped pretty narrowly for the agent to use.

2. We need sensible micropayments. The more transactional and agent in the middle the world gets, the less services can survive with webpages,apps,ads and subscriptions.

3. Local models are surprisingly capable for some tasks and privacy safe(er)... I'm hoping these agents will eventually permit you to say "Only subagents that are local may read my chat messages"

I'm a bit surprised that people need an LLM to automate things like this. Is the market really that large, to cause such a hype? I don't think I'm being "elitist" by having a calendar and a pen, am I..?

The one tangible usecase is perhaps booking things. But, personally, I don't mind paying 5-10% extra by going to a local store and speaking to a real person. Or perhaps intentionally buying ecological. Or whatever. What is life if you have a robot optimize everything you do? What is left?

If you're happy "speaking to a real person" when you could automate that interaction away somehow then no, digital personal assistants probably aren't something you're going to care about.

I love talking to real people about stuff that matters to them and to me. I don't want to talk to them about booking a flight or hotel room.

If hotels, or google, or travel websites wanted people to book programmatically they would have an api.Remember when Google search had an api? In the end the human is responsible for the purchase. I think when the dust settles, AI will offer a "do you want to purchase?" and then the human will press the button. Or ChatGPT or somebody controlling the last step will have that button, and services will accept it (like Instagram) because it brings business.
This only lasts until dark patterns can be inserted that disrupt the ease of use that agents are currently providing. If I can't force the end user to watch unskippable ads or trick them into spending money on a service they don't need, what are we even doing?
The reason they don't have an API is that they want to upsell you on other stuff, and get paid to promote their partners.

There's going to be a huge fight over how that relates to AI assistants over the next few years.

I agree fully, and wanted to add: for many of these services, like travel engine comparison sites, running the query itself costs money, so you do not want to make it to easy to search without booking.
The nuances contained in ”booking a flight or hotel room” are plenty, it matters a lot to a lot of people. The industry will probably be very very happy to have bots do it, the amount of extra revenue they will get by taking the tricks made for humans to the next level is going to be substantial.
I think part of it is the person that wrote the blog is very wealthy. They mention a personal assistant, very expensive fashion items, and hotel reservations that are 2x the price I paid for my honeymoon. Most people are probably cross shopping Walmart brand milk with name brand, and they aren’t dropping hundreds a month on an AI subscription. It’s a class thing combined with the Bay Area engineer bubble mentality —- I have some family that came from money and they just see the world completely differently, they can’t fathom life in say, Kansas at median household income.
Well websites like AirBnB tend to make it as difficult as humanly possible to automate stuff like this, so maybe?

Although that likely only lasts until they learn how to block LLMs effectively.

We may get to a point where they have a hard time distinguishing. Perhaps it can be made in their interest to open the API for everyone (i.e. convince the bean counters)
IMHO the "killer app" aspect of OpenClaw (and similar) is that everything is now an API.

We think of chat apps, like WhatsApp, as being ways to communicate with people, which is a nice way of saying they are protocols. When you want something, you send a message, and you get an answer, just like with HTTP, except the endpoints have been controlled by meat. With OpenClaw, the meat is gone. Now you can send a message on WhatsApp to schedule a date with your spouse, their OpenClaw will respond with availability, they'll negotiate a time and place. We've replaced human communication with an ad-hoc, open-ended date-negotiation protocol, using English instead of JSON as a data-interchange format, and OpenClaw as the interface library.

You can say "make an appointment at my dentist" and even if your dentist doesn't have a website, the bot can call up and schedule an appointment. (I don't know if OpenClaw can do this now, but it seems inevitable.) In other words, the (human) receptionist is now an API that can be accessed programmatically.

> We've replaced human communication with an ad-hoc, open-ended date-negotiation protocol, using English instead of JSON as a data-interchange format, and OpenClaw as the interface library.

People heralding this as a good thing is extremely disturbing.

If we insist on using that term, let's be more precise: Everything is a horrendously expensive API that will give you subtly incorrect behaviour at random.
Humans are also famous for introducing errors in their communication. I think the AI-to-AI interface will only improve on that .

The price is high now but will get cheaper, especially when compared to the cost of human labor.

Having said that, it sounds like an isolating and boring way to live.

Totally agree its basically the equivalent of a few low end apps as of now. The interesting thing to me is that it does MANY low end apps all together.

It's a calendar, reminder, notebook, fridge scanner, and a webscraper

I think the interesting idea here is that overtime this will grow to more applications. None require integration or effort to work you only need plug the infrastructure and tooling.

This to me is what will eventually wipe out most agentic startups. The enterprise version of this little thing is just a bot and a set of documents of what it should do and a few tools. Why pay and setup a new system when I can just automate what I already have?

There's a lot of irony right now regarding the cost of these things too (although I know the cost curve will drop over time). I know developers that are burning $1,000/day on tokens for Claude Code or VC's using the $200/month ChatGPT pricing plan who are then talking about Vibe coding TurboTax away. TurboTax for most people is $50 to $100 a year. We are still a far way off even from a cost justification standpoint let alone a reliability standpoint of relying on a vibe coded solution for filing your taxes.
  • enmyj
  • ·
  • 3 hours ago
  • ·
  • [ - ]
heartily agree. It takes ~10s to see what's in the freezer. Also "this is water" etc
  • ·
  • 1 hour ago
  • ·
  • [ - ]
If you're on MS stack, this is all stuff that MS 365 Copilot will already do for you, but with much better defined barriers around what it can and cant access.
This is the first positive thing I have heard about copilot. You’ve found it genuinely capable?
  • ·
  • 4 hours ago
  • ·
  • [ - ]
Assuming you are using the flagship copilot that is a $30 / mo add on to a 365 subscription, and maybe, maybe if Microsoft replaced CoPilot’s “brain” with Opus 4.5. In my experience, while flagship CoPilot does deliver value if setup correctly, it’s no where near as capable an “agent” as Claude. (And even though Open Claw is now model agnostic, there is a reason for its association to Claude. Despite it’s expense, I find Opus 4.5 works best.)
I would be surprised if Copilot is even close to that
Everything that are daily burdens and require an assistant are also the things that require the most secure way to access them. OpenClaw sounds amazing on paper but super risky in practice.
> as someone who has a chest freezer and a compulsive desire to buy too many things at costco, we take everything out of the freezer every few months to check what we have. before, this was a relatively involved process: me calling things out, my partner writing them down.

A thought I constantly find myself having when I read accounts of people automating and accelerating aspects of their life by using AI... Are you really that busy?

I mean, obviously, no one is thrilled by spending ten minutes making a dentist appointment. But I strongly suspect that most of us will feel a stronger sense of balance and equanimity if a larger fraction of our life is spent doing mundane menial tasks.

Going through your freezer means that you're using your hands and eyes and talking to your partner to solve a concrete problem. It's exactly the kind of thing primates evolved to do.

Whenever I read articles like this, I can't help but imagine the author automating away all of the menial toil in their day so they can fill those freed up minutes with... more scrolling on their phone. Is that what anyone needs more of?

The freezer one is so weird because there is an even simpler solution to the problem. Just buy less shit! If you have so much stuff that you can’t keep track then don’t have so much stuff, simple.

I think there is a common psychology when people notice a problem they first think about what they can add to solve the problem, when often the best solution is to think about what you can remove.

My main interest in something like OpenClaw is giving it access to my bank account and having it harvest all the personal finance deals.

Fortune favors the bold, I guess.

Just weeks ago, the sentiment was such that developers would be managing AI workers.

Now, it seems that AI will be managing the developers.

Nope, this is what the hype wants you to believe. You still have to do all the thinking as the current crop of AI is a tool at your disposal. A pretty impressive tool.
Or more : https://rentahuman.ai/
I wish I understood why all lowercase text and cosplaying as Zoomers became the preferred affectation of AI people.
> amongst smart people i know there's a surprisingly high correlation between those who continue to be unimpressed by AI and those who use a hobbled version of it

is it "hobbled" to:

1. not give an LLM access to personal finances 2. not allow everyone in the world a write channel to the prompt (reading messages/email)

I mean, okay. Good luck I guess.

Wait I'm ignorant, how long has OpenClaw/Clawdbot existed? This person listed like 6 months of activities that they offloaded to the bot, I thought this thing was pretty new.
  • saghm
  • ·
  • 5 hours ago
  • ·
  • [ - ]
Maybe Clawd wrote this itself, and it just doesn't know how old it is?
FWIW, the screenshots all have the dates spanning the last couple days.

But yeah, I can't imagine me getting used to a new tool to this degree and using it in so many ways in just a week.

OpenClaw utilizes AgentSkills designed by Anthropic so OpenClaw is plug and play with certain APIs and integrations.
AgentSkills were introduced in Oct 2025, so less than four months ago.
AI is useful for researching things far more quickly before making a decision and for automation/robotics. Motivated people don't need a nagbot to replace their calendar.
So if all day you spend chatting with people via IMs, then openclaw helps you automate that. Got it.
  • thm
  • ·
  • 5 hours ago
  • ·
  • [ - ]
https://www.theregister.com/2026/02/04/cloud_hosted_openclaw...

Kill it with fire - Analyst firm Gartner has used uncharacteristically strong language to recommend against using OpenClaw.

  • ·
  • 5 hours ago
  • ·
  • [ - ]
I may not be AGI, but here's a $615 2 Queen bed hotel room for the dates he wants in exactly the location he wants (just not on Airbnb).

https://www.booking.com/Share-Wt9ksz

Maybe he really is tied to $600 as his absolute upper limit, but also seems like something a few years from AGI would think to check elsewhere.

As someone for whom English is not the first language, I got stumped by the "chest freezer" and the photo of colourful bags, for good ~15 seconds, going through - "hm, must be some kind of travel thing where you bring snacks in some kind of device you carry around your neck / on your chest...why not backpack freezer then...hm, why would snacks need a freezer...maybe it's just a cooler box, but called chest freezer in some places"...

....before I took a better look of the photo and realised it's frozen stuff - for the dedicated freezer - that opens like a chest (tada).

Well, that was fun...Maybe I should get a bit more sleep tonight!

> how’d you set it up?

I was disappointed by this section. He doesn’t mention which model he uses (or models split by task type for specific sub agents).

I tried out OSS-20B hosted on Groq (recommended by a YouTuber) to test it for cheap, but the model isn’t smart enough for anything other than providing initial replies and perhaps delegating tasks into expensive capable models from ChatGPT or Claude. This is a crucial missing detail to replicate his use cases.

'the sweet sweet elixir of context is a real "feel the AGI" moment and it's hard to go back without feeling like i would be willingly living my most important relationship in amnesia'

I'm not so sure that I would use the word "sane" to describe this.

Can this thing deal with the insane way my children's school communicates? Actionable information (children wear red tomorrow) is mixed in with "this week we have been learning about bees" across five different communication channels. I'm not exaggerating. We have Tapestry, emails, a newsletter, parents WhatsApp, Arbour and Facebook.

I guess the difficulty is getting the data into the AI.

Yes, I have Claude summarize the rambling, repetitive, slightly unhinged emails from my kindergarten teacher. Otherwise I simply ignore them.
That's six channels actually.
Oh yeah it used to be five but they added Facebook because - I quote - "we hope that we can create another line of communication for reminders and messages".
Why is this written in lowercase? What a performative way to write in 2026
I just can't get over how none of this is new. 6 months ago I was running "summarize my work" tasks using linear and github mcps

just using a cron task and claude code. The hype around openclaw is wild

A lot of it is, in fact, new.

The hype around OpenClaw is largely due to the large suite of command line utilities that tie deeply into Apple’s ecosystem as well as a ton of other systems.

I think that the hype will be short-lived as big tech improves their own AI assistants (Gemini, improved Siri, etc), but it’s nice to have a more open alternative.

OpenClaw just needs to focus on security before it can be taken more seriously.

What part is new? the thing that took off is that it allows technophiles who couldn't probably flash a raspberry pi to feel like they are hackers. All of this stuff exists in tons of random AI apps that exist already it just wasn't really that much of a value add, there is just a virality of it reaching audiences that previously only knew how to use a chat app.
I wouldn’t call it new, just conveniently packaged and with more momentum. I’ve been running an apple-mcp server on a Mac Mini for Claude to use to manage my reminders in addition to Gcal + gmail, and I could have just as easily added messaging capabilities.

Call me crazy, but… I feel more likely to trust Anthropic than anybody else when it comes to safety on things like this.

To me, the magic is around interactions with personal info where they are - iMessages, e-mails, etc. I still am wart to open up like this, but it certainly is not as simple as Claude code and cron task. The “you can already do this via rsync + FTP” comment on Dropbox Show HN thread comes to mind.
It's a bit different than the Dropdox situation because the market is already flooded, the big players have their options, the cycle is rapid (who's langchain?)

I hope, think, and build towards a world where there will be fewer winner-take-all in this foundational tech

Really enjoyed this. It’s one of the most grounded takes I’ve read on OpenClaw. You skip the hype and actually show what it looks like when someone lives with it day to day, including the tradeoffs. The examples around texts turning into real actions and the compounding value of context made the case way better than any demo ever could.

Quick question: do you think something like https://clawsens.us would be useful here? A simple consensus or sanity-check layer for agent decisions or automations, without taking away the flexibility you’re clearly getting.

I some lose utility but my openclaw bot only has its own accounts. I do not give it access to any of my own accounts.
Do you mean “bullish”?
That would be the more general/traditional way of saying it, but in modern investment circles the focus seems to have turned towards the actual people being "bulls/bears" and not just the attitudes of the market. A person is a bull or a bear, as opposed to a person being either bullish or bearish.

So in this construction, a "bull case" is a "case that a bull (the person) can make".

  • ahoka
  • ·
  • 5 hours ago
  • ·
  • [ - ]
Bull and bear markets. Bull’s horns are pointing up (expecting growth, optimistic), bear’s claw is pointing down (expecting recession, pessimistic). Yeah, it’s stupid.
So they indeed meant "bullish"? That's what "bullish" means.
"Bullish" means optimistic or even aggressively optimistic. It's typically used in the context of markets.
Sane is an adjective, 'X but Y Noun' expects Y to be an adjective if X is also such. Sane/Bull Case-> Sane/Bullish Case
Right, so they probably meant bullish
"a bull case" gets lots of google results, so it seems to be a commonly used construction amongst analysts. Basically it means "The case that OpenClaw will develop as a bull".

"bullish" seems more common in tech circles ("I'm bullish on this") but it's also used elsewhere.

> let me be upfront about how much access i've given clawdbot: it can read my text messages, including two-factor authentication codes. it can log into my bank. it has my calendar, my notion, my contacts. it can browse the web and take actions on my behalf.

this is foolish, despite the (quite frankly) minor efficiency benefits that it is providing as per the post.

and if the agent has, or gains, write access to its own agents/identity file (or a file referenced by its agents file), this is dangerous

> i haven't automated anything here, but booking a table by talking to clawdbot is delightful.

Omg. Just get the phone and call the restaurant, man.

I really don't want to live in this timeline where I can't even search for b&b with my gf without burning tokens through an LLM. That's crazy.

It is impressive what people find "delightful, "a joy", "fresh air" these days.
  • cj
  • ·
  • 5 hours ago
  • ·
  • [ - ]
Tangent: what is the appeal of the “no capitalization” writing style? I never know what message the author is intending to convey when I see all lower case.

Normally I can ignore it, but the font on this blog makes it hard to distinguish where sentences start and end (the period is very small and faint).

  • dang
  • ·
  • 2 hours ago
  • ·
  • [ - ]
"Please don't complain about tangential annoyances—e.g. article or website formats, name collisions, or back-button breakage. They're too common to be interesting."

https://news.ycombinator.com/newsguidelines.html

  • 1dom
  • ·
  • 5 hours ago
  • ·
  • [ - ]
I really dislike it too.

I think it might be adults ignoring established grammar rules to make a statement about how they identify a part of a group of AI evangelists.

Kind of like how teenagers do nonsensical things like where thick heavy clothing regardless of the weather to indicate how much of a badass them and their other badass coat wearing friends are.

To normal humans, they look ridiculous, but they think they're cool and they're not harming anyone so I just leave them to it.

make a statement about how they identify a part of a group

That’s what it is. A shibboleth. They’re broadcasting group affiliation. The fact that it grates on the outgroup is intentional. If it wasn’t costly to adopt it wouldn’t be as honest of a signal.

On a scale from the purest, not lifting a finger anymore than to strike a keyboard, of virtue signaling to putting one's money where their mouth is this shibboleth is about as costly as the tidal zone is dry land.
can't imagine getting this riled up over lowercase text. some serious fist-shaking-at-clouds energy.

it's meant to convey a casual, laid back tone - it's not that big of a deal.

You convey tone through word choice and sentence structure - trying to convey tone through casing or other means is unnecessary and often just jarring.

Like look at the sentence "it has felt to me like all threads of conversation have veered towards the extreme and indefensible." The casing actually conflicts with the tone of the sentence. It's not written like a casual text - if the sentence was "ppl talking about this are crazy" then sure, the casing would match the tone. But the stodgy sentence structure and use of more precise vocabulary like "veered" indicates that more effort has gone into this than the casing suggests.

Fair play if the author just wants to have a style like this. It's his prerogative to do so, just as anyone can choose to communicate exclusively in leetspeak, or use all caps everywhere, or write everything like script dialogue, whatever. Or if it's a tool to signal that he's part of an in-group with certain people who do the same, great. But he is sacrificing readability by ignoring conventions.

It's hard to find sentence breaks, it is actually about readability and accessibility
Ironically, this sentence is called a comma splice or run-on sentence. A period or semicolon would be correct.

I agree with the sentiment too, or maybe I am getting old :P

I don't think it's about getting old, it's about expecting clear and parsable communication

Some people are being lazy, they will get less attention, ideally

I also agree it sucks, and I don't see a problem pointing it out.
It's just very poser behavior.
TIL hacker news is dominated by boomers
if by boomers you mean a community with above average expectations for the quality of submissions and commentary, sure
I thought it was a joke about a propensity to peddle public policy that will drive the world off a cliff, but not until after we get ours.
That's politicians and media influencers of all ages, not the general public

The new generation of tiktok / podcast "independent journalists" is a serious issue / case of what you describe. They are many doing zero journalism and repeating propaganda, some paid by countries like Russia (i.e. Tim Pool and that whole crew that got caught and never face consequences)

> to normal humans, they look ridiculous, but they think they're cool and they're not harming anyone so i just leave them to it.

fixed it for you! now it’s in a casual, laid back tone.

You mention the technical aspect (readability) and others have suggested the aesthetic, but you could also look at it as a form of rhetoric. I'm not sure it's really effective because it sort of grates on the ear for anyone over 35, but maybe there's a point in distinguishing itself from AI sloptext.

Incidentally, millenials also used the "no caps" style but mainly for "marginalia" (at most paragraph-length notes, observations), while for older generations it was almost always associated with a modernist aesthetic and thus appeared primarily in functional or environmental text (restaurant menus, signage, your business card, bloomingdales, etc.). It may be interesting to note that the inverse ALL CAPS style conveyed modernity in the last tech revolution (the evolution of the Microsoft logo, for example).

I was using all lowercase as my default for internet comments (and personal journal entries) for at least a solid decade, starting from some point in the 90s. I saw it as a way to take a step back from being pretentious.

I eventually ran into so much resistance and hate about it that I decided conforming to writing in a way that people aren't actively hostile to was a better approach to communicating my thoughts than getting hung up on an aesthetic choice.

Having started out as a counterculture type, that will always be in my blood, but I've relearned this lesson over and over again in many situations-- it's usually better to focus on clear communication and getting things done unless your non-standard format is a critical part of whatever message you're trying to send at the moment.

I'm a big fan of counter culture and so on, but generally the point of text is to be read and using all lower case just makes it harder for all your readers, which seems like the worst form of arrogance.
> [No-caps text] sort of grates on the ear for anyone over 35 [...] Incidentally, millenials also used the "no caps" style but mainly for "marginalia" (at most paragraph-length notes, observations)

I (a millenial) carried over the no-caps style from IRC (where IME it was and remains nearly universal) to ICQ to $CURRENT_IM_NETWORK, so for me TFA reads like a chat log (except I guess for the period at the end of each paragraph, that shouldn’t be there). Funnily enough, people older than me who started IMing later than me don’t usually follow this style—I suspect automatic capitalization on mobile phones is to blame.

  • eggy
  • ·
  • 4 hours ago
  • ·
  • [ - ]
nobody shouts in lowercase—it whispers its way into being, a small insurgency against The Proper Way To Speak ; )

-- inspired by e.e. cummings!

> Additionally, The Chicago Manual of Style, which prescribes favoring non-standard capitalization of names in accordance with the bearer's strongly stated preference, notes "E. E. Cummings can be safely capitalized; it was one of his publishers, not he himself, who lowercased his name."[65]
But then Clawd gets capitalized...
> but maybe there's a point in distinguishing itself from AI sloptext

Surprisingly, I have seen lower case AI slop - like anything else, can be prompted and made to happen!

  • nprz
  • ·
  • 5 hours ago
  • ·
  • [ - ]
Casual, informal, friendly, hip, young, etc.

Can make sense on twitter to convey personality, but an entire blog post written in lower case is a bit much.

Someone at some point styled themselves as a new E.E. Cummings, and somehow this became a style. The article features inconsistent capitalization for proper names alongside capitalized initialisms, proving there is some recognition of the utility of capitalization.

Ultimately, the author forces an unnecessary cognitive burden on the reader by removing a simple form of navigation; in that regard, it feels like a form of disrespect.

Typeface issues aside all-lowercase is about having a more conversational register, intended to indicate a chilled-out and informal vibe.

It does read as a little out of place in a serious post like the OP though.

the vibe I get is someone who can't put in the effort to make my job reading easier (i.e. hard to find sentence breaks)

It is on a human seeing level, harder to parse. If they don't want to use proper grammar and punctuation, it reflects on their seriousness and how serious I should take their writing (not at all because I'm not going to read difficult to parse text) The same goes for choosing bad fonts or colors that don't contrast enough

I’ve seen it a lot in ‘90’s hacker / net adjacent cultures. It always reads as gen-x/elderly tech millennial to me - specifically post 1993 net culture but prior to mass adoption of autocorrect.

It was the norm on irc/icq/aim chats but also, later, as the house style for blogs like hackaday.

Now I read it as one would an hear an accent (such as a New England Maritime accent) that low-key signifies this person has been around the block.

Even more recently is a minor signifier that this text was less likely generated by llm.

I think I like it generally, maybe not in this specific case, but I'm not sure why it appeals to me.

Over the last 5 years or so I've been working on making my writing more direct. Less "five dollar words" and complex sentences. My natural voice is... prolix.

But great prose from great authors can compress a lot of meaning without any of that stuff. They can show restraint.

If I had to guess, no capitalization looks visually unassuming and off-the-cuff. Humble. Maybe it deflects some criticism, maybe it just helps with visual recognition that a piece of writing is more of a text message than an essay, so don't think too hard about it.

Incidentally, prolix is a fifty dollar word. You did successfully avoid five dollar words, but you didn’t go the right direction.

It’s okay to say ‘this was too long’. Prolix???

It mildly amuses and fascinates me, because for the last decade Gladwellians and business gurus have extolled the virtues of modern English as a flat, hierarchy-less language in comparison to Japanese, Korean, etc. which causes plane crashes. And yet here we see an overwhelming desire to create hierarchy in English, so the author can pretend to be more casual and ordinary.
Its the black turtle neck of 2026
For "something that is published" (which includes a comment like this) I clearly dislike it too, but for chatting / texting, I realize that I often use it more than my interlocutors, and I'm not sure why. There's a part of lazyness I guess, but also a vague sense of "conveying the impression of a never ending stream of communication", which is closer in my mind to the essence of the chat medium. In French, there is also the additional layer of "using the accents or not".
I always start my texts with a capital, but I don't put periods at the ends of my sentences when texting

that way I can continue the same sentence in the next message if necessary

And if I need to start a new sentence I start that message with a capital.

i don't know this author but ian bremner does this. it's as if he's conveying what he believes are serious and important thoughts in an unserious and casual way, to make it appear as if the thoughts - which again he probably thinks are brilliant - just come quickly and naturally. it comes across as performative though again not making claims against this author. and yes i am not using sentence case here, but this is not an essay.
> just come quickly and naturally.

Ironically, it would take a lot of effort for me to type without capitalization and also undo capitalization auto-correct. It would not come quickly nor naturally.

They may not type it that way, you can select all and lower case all with a few keystrokes in vim. Should this be the case, it lends itself more to the performative nature of the style over clear communication
It's the equivalent of TikTokers who provide hot takes while eating food. It's done to feign being superior and aloof, e.g. "This is so easy to understand and so beneath my intellect, I can tell you about it will I eat these crackers"
George: To cover my nervousness I started eating an apple, because I think if they hear you chewing on the other end of the phone, it makes you sound casual.

Jerry: Yeah, like a farm boy.

First time I've seen it. It will be interesting to see if that trends. I can think of at least one previous case where internet writing style overturned centuries of english conventions: we used to put a double space after each period. The web killed that due to double spaces requiring extra work (&nbsp, etc), and at this point I think word processors now follow the convention.

It's always useful to check oneself and know that languages are constantly evolving, and that's A Good Thing.

The web had little to do with APA’s decision to adopt one space as the standard. It was desktop fonts in the mid-eighties. Two spaces emerged as a standard when fonts were monospaced - they were a readability hack. When proportional fonts started to be introduced, two spaces began to look visually odd. That oddness was especially apparent in groups of sentences like.

“It’s hard to learn how to spell. It takes practice, patience and a lot of dedication.”

^ In a proportional font the difference in width between ‘ll’ and ‘ ‘ is noticeable. In a monotypes font, two spaces after a period provide a visual cue that that space is different.

I think this is why this all lowercase style of writing pisses me off so much. Readability used to be important enough to create controversy - nobody cares anymore. But, I didn’t care enough to read the whole article so maybe I missed something.

> First time I've seen it. It will be interesting to see if that trends.

It's not a new trend, I'm surprised you never noticed it. It dates back to at least a decade. It's mostly used to signal informal/hipster speak, i.e. you're writing as you would type in a chat window (or Twitter), without care for punctuation or syntax.

It already trends among a certain generation of people.

I hate it, needless to say. Anything that impedes my reading of mid/long form text is unwelcome.

> I'm surprised you never noticed it

Probably due to social circles/age.

> I hate it, needless to say.

It certainly invokes a innate sense of wrongness to me, but I encourage you (and myself) to accept the natural evolution of language and not become the angry old person on your lawn yelling about dabbing/yeeting/6-7/whatever the kids say today.

> to accept the natural evolution of language and not become the angry old person on your lawn yelling about dabbing/yeeting/6-7/whatever the kids say today.

I think "accept everything new" is as closed-minded as staunchly fighting every change.

The genuinely open-minded thing to do is accept that some changes are for the worse, some for the better, think critically about the "why", and pick your battles.

  • ·
  • 3 hours ago
  • ·
  • [ - ]
It’s weird being literate enough in a language now without a bicameral script (or spaces). When I was younger, I thought this stuff wasn’t so important, but then when you learn a new language, you are trying to figure out what a “robert” is, to then be told “oh, it’s just a name”—which is obvious if know standard `en-Latn` conventions.
I've seen this before, I know Sam Altman does it (or used to do it). That was a couple years ago. Hope it doesn't become a trend.
Unfortunately it has become quite common on HN already.

It comes from people growing up on smartphone chats where the kids apparently don’t care to press Shift.

I've already written an extension that filters these comments intelligently. (E.g., quotes are ignored but if the rest of the body is all lowercase it is collapsed.)
have you shared it anywhere?
I plan to at some point, it's part of a bigger extension I created for myself to filter out minor annoyances and I'd have to strip out/modify things other people probably wouldn't want (such as filtering of "new age" TLDs like ".pizza" and whatnot).
What’s weird though is that modern OSes often auto-capitalize the first letter of a sentence, so it actually takes more effort to deliberately type in all-lowercase.
Only mobile does that in my experience - you can tell what platform people send discord messages on based on this usually
simple toggle to disable it permanently

my reasoning is that i don’t want identifiable markers for what device im writing from. so all auto-* (capitalization, correct, etc.) features are disabled so that i have raw input

Being part of the minority that disables those things (and then admitting to it in public) provides a lot more analytical signal than you’re aware of. That’s a remarkably poor reason to disrespect your readers.
i don't care about the 'analytical signal'. the purpose is people can't tell if im writing a (discord, slack, etc.) message from my phone or laptop or desktop, and it works for that
It's already a trend. It's been for at least a decade. I'm surprised people here never noticed it...
My assumption was that it's a way to convey it was written by a human because it would be hard to get an AI to write in all lowercase (which it actually isn't).
I was just this morning reading one of those navel-gazing moltbook posts where the agent describes their "soul.md", and one of its few instructions was all-lowercase (which it was doing).

That early sentence "i’ll be vulnerable here (screenshots or it didn't happen) and share exactly what i've actually set up:" reads pretty clawdbot to me.

My old CEO - ex sun/greenplum/pivotal swore that sending an email in lowercase forced the other person to read the whole message and not skim.
ItisevenbetterwhenyoudropthespacesthatREALLYforcespeopletoengagewithyourcontent. FormaaimxlgarbteihratttenionandHLODitscrmblaetheintreiorofwrdos! /s
On top of using scriptio continua, you can write your emails in ancient Greek for that truly authentic feeling.
IF YOU CAN UNDERSTAND THAT ALL CAPS IS SHOUTY, then it is easy to follow that all lower is a whisper, informal, casual way to talk. there are people who dislike all caps, i do too. i feel even capitalizing the first part of nouns and such grammar is shouty. yup. different people have different sensitivities for different things. i always liked all lower, also picked it from python_programming for a decade. so i am happy for this trend.
Perhaps it's marketing to attract those who wear sweatpants to school. The author's other posts are written normally.
It’s incredibly obnoxious. I feel like I’m ready AIM circa 2000.
For me is like a someone is trying to show me something using form instead of content.
  • ·
  • 5 hours ago
  • ·
  • [ - ]
You know how people used to wear the black turtleneck to channel Steve Jobs? This is how they channel Sam Altman (who also does this). It's just an affectation saying "I'm with Sam". There's not much more to it.
as perfect text became an indicator for AI generated content, people intentionally make mistakes (capitalization) to make their text appear more human; and its also faster
Using a semicolon like that also identifies your text as AI generated. Close but no cigar.
I have chatted with someone else, and they pointed me to a blog post (will attach if I can find).

The general idea is deliberately doing something triggering some people and if the person you're interacting with is triggered by what you're doing, they are not worthy of your attention because of their ignorance to see what you're doing beyond the form of the thing you're doing.

While I respect the idea, I find it somewhat flawed, to be honest.

Edit: Found it!

Original comment: https://news.ycombinator.com/item?id=39028036

Blog post in question: https://siderea.dreamwidth.org/1209794.html

I'm generally of the opinion that capitalization is not necessary in many cases, such as at the start of sentences. That's what punctuation is for :)
easier to type without using the shift key, and in pg you can just use LIKE not ILIKE to find the word.
Text is meant primarily to be read rather than written.
Sure, but preeminently for effortless querying in PostgreSQL.
>I never know what message the author is intending to convey when I see all lower case.

JUST IMAGINE A FACEBOOK POST THAT IS WRITTEN IN ALL CAPS AND THEN INVERT THAT IMAGINATION.

  • sdwr
  • ·
  • 5 hours ago
  • ·
  • [ - ]
Informal, casual, friendly
It comes across as unfriendly to me.
I view it as lazy or uneducated.
In a blog post it makes the author sound foreign at best and uneducated at worst, with sloppy being halfway in between.
i dislike pressing shift, especially on non-ergo (non-thumb) keyboards where it uses my pinky.
  • kypro
  • ·
  • 3 hours ago
  • ·
  • [ - ]
No idea, but it's something I've been thinking about ever since my parents dug out an old school journal from when I was younger and they were laughing about the stuff I wrote in there... The first 50 pages or so were full of laughably simple phrases like, "played with sand" or "i like computers".

Later in the journal my writing "improved". Instead I might write, "Today I played in the sandpit with my friends."

I vaguely remember my teacher telling me I needed to write in full sentences, uses the correct punctuation, etc. That was the point of these journals – to learn how to write.

But looking back on it I started to question if I actually learnt how to write? Or did I just learn how to write how I was expected to?

If I understood what I was saying from the start and I was communicating that message in fewer words and with less complexity, was it wrong? And if so wrong in what sense?

You see this with kids generally when they learn to speak. Kids speak very directly. They first learn how to functionally communicate, then how to communicate in a socially acceptable way, using more more words.

I guess what I'm trying to say is that I think the fact you can drop capitals and communicate just as effectively is kinda interesting. If it wasn't for how we are taught to write, perhaps the better question to ask here is why there are even two types of every letter?

  • cma
  • ·
  • 4 hours ago
  • ·
  • [ - ]
Altman/Brockman did it a lot and it became popular. I don't remember if it is true or "Malcolm Gladwell" true, but in various stories all NBA players started wearing baggy shorts because Michael Jordan did for one reason or another, like wearing his college shorts under them.
Makes you reduce your guard to clearly AI generated content.
informality, humanity — we're in an age where we can't assume anything is written by a person anymore
Tangent to the tangent!

I've started using it professionally because it signals "I wrote this by hand, not AI, so you can safely pay attention to it."

Even though in the past I never would have done it.

In work chats full of AI generated slop, it stands out.

Trivial to get AI to write in all lowercase, though.
Yes, the strategy depends on lack of effort from other senders, even trivial effort
> In work chats full of AI generated slop, it stands out.

Do you mean like Teams AI autocomplete or people purposefully copying AI-generated messages into chats?

The latter. Using chatgpt to write their chat messages usually. Emoji, arbitrary bold and italics, bullets, etc.
it's a billionaire thing. look at the Epstein email threads. too lazy to check +typos allovr .
  • PKop
  • ·
  • 4 hours ago
  • ·
  • [ - ]
[flagged]
Its a gen z trend. My nephews do the same. We are old.
We are not old, there is a reason the generation is said (in stats and polls) to be less professional than prior generations when entering the workforce
> less professional than prior generations when entering the workforce

Every older generation says that about the next.

It’s older than that - lots of my boomer bosses did it to seem cool over email in the late 90s.

I viscerally remember starting my day with my inbox saying “cum c me”… I know what you’re trying to do, bro, but damn.

We are young and old all at the same time.

I remember hearing that people used it as a way to signal that they were too busy, too on the go, too important to use proper punctuation..it was an obnoxious c suite trend as long as I can remember. Like you're always trying to signal that you were doing all of your comms from your cell phone between meetings/travelling. Given this article's tone and content I would say that what the author is trying to emulate or convey , maybe subconciously.
Interesting. I am a millennial and I never did this, nor did I have any friends that did. But I know m nephews deliberately turn off the auto edit in there iphones.
Turning off the auto correct is really interesting, I wonder if there's any kind of study on that
  • dcre
  • ·
  • 4 hours ago
  • ·
  • [ - ]
Fine article but a very important fact comes in at the end — the author has a human personal assistant. It doesn't fundamentally change anything they wrote, but it shows how far out of the ordinary this person is. They were a Thiel Fellow in 2020 and graduated from Phillips Exeter, roughly the most elite high school in the US.
The screenshots of price checks for a hotel charging $850 a night is what tipped me off. The reservations at expensive bay area restaurants, too.

I have a guess for why this guy is comfortable letting clawdbot go hog-wild on his bank account.

Kind of funny to say you helped make the Harvard CS curriculum and then dropped out. Your own curriculum was not good enough for you? Probably extenuating circumstances, but still seems funny.
When I saw them buying $80 Arc'teryx gloves that was enough for me.
  • nunez
  • ·
  • 2 hours ago
  • ·
  • [ - ]
Exeter had a hella good policy debate team back in the day. Probably still do; I've been out of the loop for a while.
Yeah, I've found AI 'miracle' use-cases like these are most obvious for wealthy people who stopped doing things for themselves at some point.

Typing 'Find me reservations at X restaurant' and getting unformatted text back is way worse than just going to OpenTable and seeing a UI that has been honed for decades.

If your old process was texting a human to do the same thing, I can see how Clawdbot seems like a revolution though.

Same goes for executives who vibecode in-house CRM/ERP/etc. tools.

We all learned the lesson that mass-market IT tools almost always outperform in-house, even with strong in-house development teams, but now that the executive is 'the creator,' there's significantly less scrutiny on things like compatibility and security.

There's plenty real about AI, particularly as it relates to coding and information retrieval, but I'm yet to see an agent actually do something that even remotely feels like the result of deep and savvy reasoning (the precursor to AGI) - including all the examples in this post.

I feel bad for whoever gets an oncall page that some executive's vibe coded app stopped working and needs to be fixed ASAP.
> Typing 'Find me reservations at X restaurant' and getting unformatted text back is way worse than just going to OpenTable and seeing a UI that has been honed for decades.

Your conflating the example with the opportunity:

"Cancel Service XXX" where the service is riddled with dark patterns. Giving every one an "assistant" that can do this is a game changer. This is why a lot of people who aren't that deep in tech think open claw is interesting.

> We all learned the lesson that mass-market IT tools almost always outperform in-house

Do they? Because I know a lot of people who have (as an example) terrible setups with sales force that they have to use.

Sure, but that also means they’re well-positioned to do a comparison.
Elites live in a different world from you and I.
You do understand that is who you’re competing with now right?

My daughter is a excellent student in high school

She and I spoke last night and she is increasingly pissed off that people who are in her classes, who don’t do the work, and don’t understand the material get all A’s because they’re using some form of GPT to do their assignments, and teachers cannot keep up

I do not see a world in the future where you can “come from behind” because all of the people with resources are increasingly not going to need experts who need money to survive to be able to do whatever they want to do

While that was technically true for the last few hundred years it was at least required to deal with other humans and you had to have some kind of at least veneer of communal engagement to do anything

That requirement is now gone and within the next decade I anticipate there will be a single person being able to build a extremely profitable software company with only two or three human employees

Ironically I feel like this may force schools to get better at the core mission of teaching, vs. credentialing people for the next rung on the ladder. What replaces that second function remains to be seen.
>She and I spoke last night and she is increasingly pissed off that people who are in her classes, who don’t do the work, and don’t understand the material get all A’s because they’re using some form of GPT to do their assignments, and teachers cannot keep up

How do they do well on tests, then?

Surely the most they could get away with is homework and take-home writing assignments. Those are only a fraction of your grade, especially at “excellent” high schools.

>You do understand that is who you’re competing with now right?

No. I'm competing with no one.

You may think you are not competing. The people whose money you may want (employers, investors, customers) definitely see you as one of many competitors for their funds.
Exactly
  • dang
  • ·
  • 2 hours ago
  • ·
  • [ - ]
[stub for offtopicness]
> it's hard to go back without feeling like i would be willingly living my most important relationship in amnesia.

This made me think this was satire/ragebait. Most important relationship?!?

Another victim of AI psychosis. I think this is actually becoming a huge problem among tech enthusiasts and I’m increasingly worried about it.
it's growing among all groups, where the wave is leading depends on the adoption within demographics. I expect long term we will see similar patterns as we do with drug abuse and crime (i.e. high correlation with poverty and all the things tied to growing up struggling)
Normal people don't feel the need to characterize their own blog posts as "sane"
[flagged]
This is a bot account. Last post in 2024, then in the last 25 minutes it has spammed formulaic comments in 5 different threads. If you were not able to instantly recognise this post as LLM-generated, this is a good example to learn from, I think. Even though it clearly has a prompt to write in a more casual manner, there's a certain feel to it that gives it away. I don't know that I can articulate all the nuances, but one of them is this structure of 3 short paragraphs of 1-2 sentences each, which is a favorite of LLMs posting specifically on HN for some reason, together with a kind of stupidly glazy tone ("killer app", "always felt 5 years away", randomly reinforcing "comparison to a human assistant you've never met" as though that's a remotely realistic comparison; how many people in the world have a human assistant they've never met and trust with all of their most sensitive information?).
  • dang
  • ·
  • 2 hours ago
  • ·
  • [ - ]
Thanks, we've banned it and some related accounts.

All: generated comments and bots aren't allowed here. https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...

for me, it's the bullet points with bold one-word sentences
[dead]
That's why it doesn't seem worth it if you are not running the model locally. To really get powerful use out of this you need to be running inference constantly.

The pro plan exhausts my tokens two hours into limit reset, and that's with occasional requests on sonnet. The 5-8x usage Max plan isn't going to be any better if I want to run constant crons, with the Opus model (the docs recommend using Opus).

Good Macs are thousands but Im waiting to find someone who's showing off my dream use case to jump at it.

>Having something that can actually parse "yep lets do 4pm tomorrow" from texts and create calendar holds is the kind of thing that's always felt 5 years away.

Isn't that just Google Assistant? Now with Gemini it seems to work like a LLM with tools.