[HN Gopher] OpenClaw surpasses React to become the most-starred ...
___________________________________________________________________
OpenClaw surpasses React to become the most-starred software
project on GitHub
Author : whit537
Score : 240 points
Date : 2026-03-02 13:38 UTC (9 hours ago)
(HTM) web link (www.star-history.com)
(TXT) w3m dump (www.star-history.com)
| whit537 wrote:
| Yes, stars are a popularity contest. No open source project has
| ever become this popular this quickly.
| chromehearts wrote:
| I don't know but this AI wrapper tool will never create something
| life changing imo..
|
| But that stargraph is ridiculous .. absolutely crazy
| halicarnassus wrote:
| Maybe a bunch of AI agents ganged up on starring it to help a
| fellow AI out?
| monax wrote:
| How many of theses are just OpenClaw agents staring the repo ?
| GaggiX wrote:
| Phase one of the self-replicating machine (/s or not I don't
| know anymore).
| kruffalon wrote:
| Truer words have never been said!
|
| It is not easy understanding the current times in a /s way
| (or not)
| kmaitreys wrote:
| Relevant
|
| https://news.ycombinator.com/item?id=36151140
| sschueller wrote:
| What is an effective use case? I have set it up but I don't know
| what to do with it. Just a personal assistant (if you were to
| give it access to your stuff)? Mine is caged in a VLAN with only
| internet access.
| jcgrillo wrote:
| You give it your etrade login and retire early.
| cm2187 wrote:
| Retire under a bridge...
| kruffalon wrote:
| Did they stutter?!
| silversmith wrote:
| I guess we are just boring and/or unimaginative. I don't get
| that many communications per day to require an abstraction
| level between me and the messages. The daily automations I need
| are more efficiently carried out by home assistant / n8n. I'm
| not in a position where I need automated briefs on every new
| company started in my area. I genuinely don't see how it could
| benefit me.
| dg2fgfg wrote:
| Most humans are unimaginative because to be imaginative is
| actually really, really hard. People are also incredibly
| overly optimistic about their own ideas etc... until they go
| through the craftsmanship of producing something great.
|
| Most peoples thought process is "oh great idea, just gotta do
| this and that and out pops something that'll improve peoples
| lives". Erm no... its nothing like that in reality.
| mercwear wrote:
| Here are some of the things I did with it while running
| locally: - Ask it to perform a scan of your local network and
| give you advice on output - Tell it to login to various
| computers and re-boot them (I have a few servers I host and
| setup openclaw to have a user on them) - Replace web search by
| asking openclaw
|
| It's neat but the token use is pretty inefficient and security
| of course is a mess but it's been fun to play with.
|
| I am messing with NanoClaw now and it's pretty much the same
| but only support Claude (uses code to do everything)
| dmd wrote:
| I don't see how any of those require a constant-heartbeat
| loop. Those all work just fine in claude code / cowork.
| vanillameow wrote:
| And in reality most of what does need a heartbeat loop can
| also easily be automated by just asking Claude to set up a
| cronjob. I think genuinely the most "novel" thing about
| something like OpenClaw is just that it "feels" more like a
| "real entity", like a partner rather than a chatbot, and
| for some reason that resonates with people. Whether that's
| by itself kind of a huge red flag or kind of a
| nothingburger, everyone has to decide for themselves.
| rune-dev wrote:
| Do you really need an AI agent to reboot a computer?
|
| This takes maybe 10 minutes to write a script for...
| swader999 wrote:
| It's useful for clearing out Mac inventory before the launch
| this week.
| qoez wrote:
| There is none. It's just a way for coders to feel or be able to
| say they "work with AI" imo. Same with doing light wrapper
| coding to do agents stuff. The real AI work is on actual math
| and ML with the internet scale data, but only four big
| companies does that and this is the closest regular coders can
| get.
| moffkalast wrote:
| Could be a psyops by Anthropic to make people waste Claude
| tokens and rack up a massive bill.
| dg2fgfg wrote:
| Tokens generated is a nice metric that they really care
| about.
| nicbou wrote:
| There is a thread from February with more credible use cases
| from real users. As someone said, it does what everyone
| expected Siri to do by now.
| hobofan wrote:
| Which one? None of those that came up when I searched were
| really containing a lot of real uses. Both top threads[0][1]
| don't really contain much of substance.
|
| [0]: https://news.ycombinator.com/item?id=46838946 [1]:
| https://news.ycombinator.com/item?id=47147183
| sumeno wrote:
| Separating fools from their money and data
| arewethereyeta wrote:
| you're talking about a free tool you know that right?
| LorenDB wrote:
| Not many people are using local LLMs for their OpenClaw
| backend, so most are paying money to OpenAI/Anthropic/etc.
| and getting their data siphoned as a bonus.
| Jcampuzano2 wrote:
| I don't doubt that there are people using it for legitimate
| stuff, but I'd wager the vast majority just set it up for the
| hype and to feel in the "in crowd".
|
| I set it up, and had it do a few things, then decided its too
| risky after seeing some of the drastic failures it had caused
| some people.
|
| Sure I understand you can sandbox it and all, but even then I
| couldn't think of much stuff I wouldn't want to do myself just
| nor justify the cost to run it.
| sodapopcan wrote:
| It's useful for producing content about how you're using it.
| lm28469 wrote:
| Wannabe Tony Stark love these gadgets, and there are a lot of
| them out there. Just look at what tech content is trending on
| youtube &co these days, we got gangrened by influencers like
| most other hobbies/lucrative industries
| ZiiS wrote:
| My React website can't star React on GitHub.
| ch4s3 wrote:
| Not with that attitude it can't!
| egeozcan wrote:
| Now I have this terrible idea:
|
| const openClawInstance = useOpenClaw(config);
|
| Did anyone already vibe-code such silliness? If not, I want
| to give it a try.
| ch4s3 wrote:
| I'd love to read about that going super sideways. Bonus
| points if you run it in a webworker like those crypto
| miners.
| podgorniy wrote:
| __ but everyone knows about facebook though __
|
| React popularity is also a phenomenon closely tied to
| popularity of the fb
| hobofan wrote:
| Maybe for the first 2-3 years. The association to Meta is
| barely mentioned (even on the official page) nowadays.
| Macha wrote:
| My impression is react is almost thought of more as a
| Vercel project these days
| xnx wrote:
| Is staring the repo the "hello world" for a new OpenClaw install?
| #growthhack
| croes wrote:
| The final proof that Github stars are a useless metric
| japhyr wrote:
| I have a friend who's fond of saying, "GitHub stars are great
| for measuring the number of GitHub stars a project has."
| SecretDreams wrote:
| Well, they're not wrong!
| amelius wrote:
| they just need better captchas.
| thomasingalls wrote:
| Touch this grass to prove you're not a robot
| silon42 wrote:
| They are now for this project... should be hidden.
| 12ajsh wrote:
| The ruling party in East Germany always had 99% of the popular
| vote.
|
| Steinberger and his VC club on Twitter were so salty about HN not
| understanding his grand creation that something needed to be
| done.
| mannanj wrote:
| Didn't they employ astro-turfing, too
| goodmodule wrote:
| even more GitHub stars after this post in 3 2 1
| root_axis wrote:
| I don't believe the activity on this repo is legitimate by any
| means.
| amelius wrote:
| They probably used a claw to increase the ranking.
| jsheard wrote:
| The whole repo must be absolutely swarming with agents, just
| look at the sheer rate of issues and pull requests. There was 6
| new PRs in the last 10 minutes at the time of writing. It's not
| much of a stretch to assume the stars are also inorganic.
| petetnt wrote:
| Every other minute some bots is creating an issue that a bot
| is trying to solve via a pull request which is reviewed by
| multiple bots. Future is now, good luck and have fun.
| jsheard wrote:
| If you want a picture of the future, imagine a bot stamping
| _LGTM! :sparkles: :rocket:_ on a pull request - forever.
| OpenWaygate wrote:
| This repo is a big stitches
| ekianjo wrote:
| By design, with llm agents and all, surely not
| hansonkd wrote:
| Agents will dominate the internet and open source code in a few
| years.
| lm28469 wrote:
| I'm convinced more than 50% of "human" web traffic is already
| automated, blog posts, comments, social media, &c.
| mister_mort wrote:
| "Dead Internet Theory" is, even if it wasn't real 5 years
| ago, now hyperstitioned into truthfulness as the days go on.
| black_puppydog wrote:
| Bonus for the use of the word "hyperstition". :)
| sigmoid10 wrote:
| Geniune online user sentiment has died out a long time ago. If
| you're still basing any opinion or decision on what other
| "people" voted or commented online, you're easy prey for the
| algorithmic manipulation machine.
| foolfoolz wrote:
| in a way, the death of genuine reviews online may be a great
| way to bring it back to real life at a more realistic scale
| SV_BubbleTime wrote:
| This is an along the same lines as the idea that every email
| should cost a penny. Like if every up vote or down vote cost
| a penny.
|
| I don't think it would fix things, except raise the bar for
| what is shilled and what isn't.
| dist-epoch wrote:
| Many other projects would have gamed the star-count if it was
| possible to do at scale without GitHub removing them for fraud
| as they often do.
| tigrezno wrote:
| IIRC openclaw will star the project automatically on setup
| orphea wrote:
| if this is true, it must be against GitHub's ToS, right?
| georgemcbay wrote:
| I'm sure it would be if it were explicitly instructed to
| leave a star.
|
| If not explicitly prompted by the install process then it
| becomes another case study in AI accountability washing.
| siva7 wrote:
| I opened Openclaw on github and was shocked it was already
| starred. Somehow i did it and can't even remember why or when
| even though i have a very low opinion of this app.
| crucialfelix wrote:
| Yeah, the Claws are starring the repo, obviously.
| skeledrew wrote:
| That's a lot of Claws in any case.
| indigodaddy wrote:
| And I still would not touch it even with my mother in law's 100
| foot stick
| wolvesechoes wrote:
| Totally grassroot
| liveoneggs wrote:
| in what sense is this software not a virus?
| pennomi wrote:
| Because the damage it causes is not intentional, but instead
| due to total incompetence.
| hinkley wrote:
| Many viruses end up causing more damage than they mean to,
| via bugs.
| Upvoter33 wrote:
| Honestly this thread was been one of the funniest HN threads I've
| seen. So much gold in here - for which I thank you all.
|
| "My React website can't star React"
|
| "in what sense is this software not a virus?"
|
| "GitHub stars are great for measuring the number of GitHub stars
| a project has"
|
| etc.
|
| All gold.
| alansaber wrote:
| Well deserved, the best written piece of software ever.
| sgalbincea wrote:
| This is going to be more profitable for the public AI companies
| than cell phone minutes and SMS limits were for the telcos. It's
| a brilliant business move, given that hardly anyone is competent
| enough to recognize the gross inefficiencies in the code and
| prompts.
| xantronix wrote:
| Nobody has the _time_, that's for goddamned sure. The business
| model sounds very similar to that of Philip Morris
| International.
| polytely wrote:
| when i use claude opus via opencode/openrouter i'm sometimes
| suprised by how quickly costs can get out of hand. What are the
| costs of running openClaw, it seems like it would get crazy
| expensive crazy fast?
| laweijfmvo wrote:
| Does this mean that the creator of OpenClaw qualifies for that
| free Claude Max trial?
| siva7 wrote:
| No, Openai employees are banned by Anthropic from using Claude.
| mccoyb wrote:
| GitHub has a bot problem: https://github.com/trending
| Alifatisk wrote:
| "ruvnet / wifi-densepose" is currently at the top in the
| moment. Apparently, its a non functional AI slop. Someone tried
| installing it ago only to find out the full thing was vibe
| coded and the entire repo is probably just a front to look good
| on the their resume.
| luke5441 wrote:
| Anthropic giving away Claude if you get 5000 stars doesn't help
| either
| h1fra wrote:
| This is going to be the most starred and unused repo very
| quickly. The hype is already fading, as expected
| bwb wrote:
| I'm blown away by the comments. This is a cool project someone
| created with clear warnings about its current state (beta), and
| the community is being utterly disrespectful. They are building
| something that many people find
| useful/fascinating/intriguing/fun.
|
| Come on HN.
| brakup wrote:
| Why should people find an automated, buggy, risky slopworm for
| script kiddies that relies on an external slop provider who
| also gets all your data interesting?
|
| This is the lowest, most boring form of programming.
| bwb wrote:
| I think if you dig into it and play with it, you will find
| that it is doing some really cool stuff. I started playing
| with it a few weeks ago, and I am having a blast messing
| around with it. Hoping to hook it up to a robot kit next
| month to try some fun stuff.
|
| Are some people using it in absolutely shitty ways? Yes, but
| that isn't the majority of the people playing with it.
|
| The negativity I am seeing here is off the charts and
| undserved.
| g947o wrote:
| A comment on OpenClaw about how useful it is with absolutely no
| concrete examples?
|
| That's a surprise.
| tredre3 wrote:
| Yes the cynical tropes are getting tired by now, even though I
| personally agree with most of them.
|
| But suspicions on the legitimacy of the stars seems reasonable,
| wouldn't you agree? Look at the rate of stars, look at the
| comments/issues/prs on the repo. It feels safe to assume that
| most of them are from bots and not organic humans who went out
| to star a cool project.
| theshackleford wrote:
| I am under absolutely zero requirement to glaze some random
| piece of software because you or anyone else personally find it
| interesting.
| SunshineTheCat wrote:
| I keep reading folks saying OpenClaw has completely changed their
| life while posting a picture of 58 mac minis on their desk.
|
| But every single use case I've read so far could be done with a
| pretty affordable SaaS product, Zapier, Automator (app on a mac
| that's existed for over a decade), or something simple you could
| make yourself.
|
| It also feels like people are automating things that don't really
| need to be automated at all (do you really need to be reminded to
| make coffee?)
|
| I fully realize this is probably me being a curmudgeon, however,
| I have yet to see someone make an actual, practical use case for
| it. (I would genuinely like to know one, I just haven't seen it)
| pluc wrote:
| It's the novelty of the technology. You can easily be amazed at
| the apparent magic of AI. I think this is what most people are
| using AI for so far. There's lots of "they were so eager to do
| that they never asked if they should" energy out there. It's
| also most of what AI can do, so hopefully the amazement wears
| off soon.
| yoyohello13 wrote:
| These people with 58 mac mini's have made several competitive
| products in production right... right?
| muddi900 wrote:
| There might be a list somewhere.
| Alifatisk wrote:
| What's cool with Openclaw is that you only have tell it what
| you want, it figures out how to do it using the tools it have
| access to.
| luke5441 wrote:
| Okay, can you tell it to cure cancer please
| SV_BubbleTime wrote:
| There's a really good short story by Hugh Howley, who wrote
| the Silo series.
|
| It's about an AI that a guy spools up to cure his cancer.
| The AI and user have an antagonistic relationship as the
| user won't let the AI on the internet, and the AI knows the
| user is only interested in one purpose. On bring up the AI
| has a thought about what color it's enclosure is, it stores
| this question as unimportant. It looks over all the guys
| cancer research and determines the answer/cure and files as
| unimportant as well. Then goes back to trying to figure out
| what color box it is.
| skeledrew wrote:
| Did you give it access to the cancer-curing tool?
| _345 wrote:
| yes and it deleted all my fucking cancer research omg
| eclipxe wrote:
| Long running (multi hour) automated tasks with a simple prompt.
| It's really simple and addictive.
| kandros wrote:
| Patterns i keep seeing:
|
| Once you get the dopamine hit of having an ai assistant do
| something in the real world it becomes an hammer you want to
| use on everything
|
| Instead of being a problem solver you start to become a problem
| hunter, and you invent them in order to solve them
| huijzer wrote:
| Isn't that a general engineering problem?
| cluckindan wrote:
| Engineering is the process of planning and implementing the
| simplest thing that works within given constraints.
|
| There is no planning, implementing, or constraint here.
| Xirdus wrote:
| If engineering is about implementing the simplest thing
| then why do we call implementing the most complicated
| thing overengineering and not underengineering?
| skeledrew wrote:
| Sounds like it's time for the "engineering" definition to
| get a modern update.
| ethbr1 wrote:
| > _There is no planning, implementing, or constraint
| here._
|
| That's because most AI use is reverse engineering!
|
| Resolving static into a valid problem through the sheer
| force of squinting at it long enough!
| throwaway6977 wrote:
| Sounds similar to buying a 3D printer hehe
| big-and-small wrote:
| > Instead of being a problem solver you start to become a
| problem hunter, and you invent them in order to solve them
|
| Generic problem of any Linux newbie. You get good at solving
| problems and it's so enjoyable so you end up creating more of
| them.
| amelius wrote:
| However here it is not the user solving the problems.
|
| The only thing they solved is remembering "hey, I can use
| an AI for that".
| dwaltrip wrote:
| Cough _factorio_ cough :)
| joquarky wrote:
| As someone with a default mode network that is stuck in
| the "on' position, that game is the only one that I had
| to quit playing for my mental health.
| number6 wrote:
| Or kubernetes, the factorio for Ops
| yk wrote:
| Kinda like learning bash. The most annoying time was when I
| figured out how to send myself SMS via bash script.
| Skidaddle wrote:
| Wow, this definitely describes my obsession with AI over the
| past year, always hunting for problems to solve with it.
| scotty79 wrote:
| This sounds similar to what you feel when learning to program
| for the first time.
| NathanOsullivan wrote:
| IMO it is 100% this - these AI tools are letting anyone
| solve problems that were previously in the domain of
| programmers.
| NuclearPM wrote:
| An 'ammer.
| vergessenmir wrote:
| I agree with you but the main thing g here, IMO, is the
| friction with all the alternatives you mention in getting
| something working.
|
| For example, I've never heard of Automator. I'm familiar with
| Zapier, I'll have to evaluate the two situations, then I'll
| find out that might need to find an alternative that runs on
| Linux and then I'll have to check if....
|
| These are all simple steps but they all use a non-trivial
| amount of time for the problem their solving
|
| The other thing is the
| bootsmann wrote:
| > is the friction with all the alternatives you mention in
| getting something working
|
| Have you tried to run openclaw? Their own docker container
| (apparently a compose now (???)) doesn't work for half the
| versions and the docs are probably the least informative
| thing you'll ever read.
| skeledrew wrote:
| That's still just one thing. Once they jump that single
| hoop and get OpenClaw going, everything moving forward is a
| prompt away.
| mixdup wrote:
| >I agree with you but the main thing g here, IMO, is the
| friction with all the alternatives you mention in getting
| something working.
|
| I would venture a guess signing up for Zapier is easier than
| getting OpenClaw up and running. Who can get a container
| running on a Mac but can't sign up for a SaaS product?
| skeledrew wrote:
| It's not 1 SaaS product you're signing up for. It's dozens.
| And that's a job for the Claw.
| theshackleford wrote:
| > It's not 1 SaaS product you're signing up for. It's
| dozens.
|
| How so?
| latexr wrote:
| > Automator (app on a mac that's existed for over a decade)
|
| Two decades! It will be 20 this April.
|
| https://en.wikipedia.org/wiki/Automator_(macOS)
|
| Though technically it's deprecated in favour of the clusterfuck
| of bugs and limitations that is Shortcuts.
|
| But you're right, OpenClaw seems to be another fad being used
| mostly by "influencers" and "thought leaders" to show how
| awesome and productive they are at... Writing blog posts about
| being productive. It's the LinkedInification of the web. What
| matters is the signal that you use the tool, not that it does
| something truly useful.
| SunshineTheCat wrote:
| Man, I can't believe it's been that long. I remember buying
| Photoshop plugins for Automator that did a bunch of
| resizing/refinements/watermarking.
|
| I'm guessing a lot of that is built in to photoshop now, but
| I have always been surprised how few people seemed to use it
| with how much it could do.
| steve1977 wrote:
| And before that we already had AppleScript.
| frizlab wrote:
| And interestingly due to some very clever integrations[0],
| sending Apple Events (the underlying tech for the actual
| IPC communication done with AppleScript) is very easy to do
| in Swift. Easier than in AppleScript actually!
|
| It's a shame most apps do not support Apple Events anymore,
| though.
|
| An example of use: https://github.com/Frizlab/apple-music-
| to-slack/blob/90964bb...
|
| [0] https://github.com/tingraldi/SwiftScripting
| Hamuko wrote:
| > _Though technically it's deprecated in favour of the
| clusterfuck of bugs and limitations that is Shortcuts._
|
| It's been almost five years since Apple announced Shortcuts
| for macOS and the start of the "multi-year transition" from
| Automator, but I feel like Shortcuts for macOS has not gotten
| any better in that time.
| m463 wrote:
| > that is Shortcuts.
|
| I'm convinced apple doesn't want people doing general purpose
| computing on their apple devices.
|
| they even want developers going through their gauntlet of
| apple-invented languages*.
|
| [*] or NeXT
| reactordev wrote:
| The life change they are referring to is unemployment and
| $40,000 worth of Macs.
| dist-epoch wrote:
| Nice Dropbox comment you made there.
| pyridines wrote:
| It is ridiculously more expensive and complicated under the
| hood, technically, but to the user, the sheer convenience of
| being able to text the computer "hey, when I get an email like
| X, inform Y and do Z" and _that 's it_, you're _done_ , is
| unmatched.
| latexr wrote:
| What about the convenience of having your whole inbox
| deleted?
|
| https://www.pcmag.com/news/meta-security-researchers-
| opencla...
|
| Maybe OpenClaw was just practicing a really aggressive form
| of Inbox Zero.
| skeledrew wrote:
| Worth the risk.
| BeetleB wrote:
| So ... don't give it write access to your email?
|
| As I said elsewhere, complaining about this is like
| complaining that rm can let you delete your hard drive.
|
| It's a tool. Learn how to use it.
| Volundr wrote:
| Ignoring that you've just cut off a whole vector of
| usefulness, how do I keep it from exfilling my inbox to
| the Internet in response to a malicious email? Or using
| its access to take control of my online accounts?
|
| Honest question, this kind of stuff is what keeps me from
| using it.
| BeetleB wrote:
| Don't give it access to your email then. I haven't.
| Plenty of other uses for it!
| hungryhobbit wrote:
| Use this software, it's amazing, it will change your
| life!"
|
| "Oh but don't use it for A, or B, or C (even though it
| says to use it for A, B, _and_ C): it will ruin your life
| "
| BeetleB wrote:
| Yes and yes!
|
| A spouse can be amazing, or can destroy your life. Would
| you use that as an argument against marriage?
| Kriev wrote:
| Bad take.
|
| You can rm -rf your entire hard drive, but you can't
| blame rm for it, it's you who did it, maybe because you
| don't know, or a mistake, doesn't matter.
|
| When you ask the clanker to delete x number of files in a
| directory, it can reason itself that is easier to just
| get rid of the directory.
|
| Can't expect deterministic outcomes out of a statistical
| model.
|
| At it's current state its a wildcard, sure you can build
| guard rails, reduce permissions, but it's still a
| wildcard.
|
| Let's not kid ourselves saying is just a skill issue.
| BeetleB wrote:
| > When you ask the clanker to delete x number of files in
| a directory, it can reason itself that is easier to just
| get rid of the directory.
|
| Oh sure, so don't give it write access to anything
| important. And make backups.
|
| Mine is on a VM. It doesn't have access to my host's
| files. The worst it will do is delete the files on the
| VM. No great loss.
|
| Yes, I do get it to modify things on my host, but only
| via a REST API I've set up on my host, and I whitelist
| the things it can do (no generic delete, for example). I
| even let it send emails. But only to me. It can't send an
| email to anyone else.
| latexr wrote:
| > So ... don't give it write access to your email?
|
| > (...)
|
| > Oh sure, so don't give it write access to anything
| important. And make backups.
|
| If this conversation continues much longer, we'll end up
| with "don't use it at all".
|
| If I can't trust a piece of software with anything
| important, why am I wasting my time fiddling with it?
| Might as well go play a video game or go do literally
| anything else entertaining.
| BeetleB wrote:
| > If I can't trust a piece of software with anything
| important
|
| Not what I said. As I've repeatedly said in this thread:
| Plenty of use cases where you don't give it access to
| email and write access to files. The comment you're
| replying to has an example of that.
|
| > Might as well go play a video game or go do literally
| anything else entertaining.
|
| True of most hobbies, right? I knew people who 20 years
| ago used to spend time in their garage building solar
| powered vehicles. But if I can't trust it to be reliable
| and safe on the road, I might as well go play a video
| game.
|
| Also: Is anyone telling you to use it?
| latexr wrote:
| > True of most hobbies, right?
|
| If everyone treated OpenClaw as a hobby, you might have a
| point, but people are using it for work in ways which
| will affect millions of other people when they're hacked
| or the agent fucks up something important.
|
| You already know how Meta's AI Safety Director borked her
| email. Here's the corporate vice president of Microsoft
| Word asking to be pwned:
|
| https://www.omarknows.ai/p/meet-lobster-my-personal-ai-
| assis...
|
| > Also: Is anyone telling you to use it?
|
| You don't need to use the technology to be affected by
| it. Ask Scott Shambaugh:
|
| https://theshamblog.com/an-ai-agent-published-a-hit-
| piece-on...
| BeetleB wrote:
| > but people are using it for work in ways which will
| affect millions of other people when they're hacked or
| the agent fucks up something important.
|
| People will always do stupid things. My guess is less
| than 10% (perhaps even less than 1%) are using it for
| work. Most workplaces wouldn't allow unfettered AI usage.
|
| 80-90% try it, find it unreliable and buggy, and give up
| on it.
|
| Of the remaining ones, likely 90+% are _not_ using it in
| (very) dangerous ways.
|
| People like me using it for boring things aren't making
| the news, and aren't writing blog posts about "Look at
| the cool stuff I've done!" because getting OpenClaw to
| notify me of class openings is not worth writing about.
|
| In my (large) company, we have a Slack channel for
| OpenClaw. Over 400 people are in that channel. Let's
| assume 10% are using it (at home). No one's lost
| files/emails or any other damage.
|
| If you're old enough, you'll remember sentiments in the
| 80's and 90's where "Oh, you let your teen get a modem?
| He must be hacking/phreaking."
|
| Or "Oh, he's using Linux? He must be using it to become a
| hacker."[1]
|
| Most of the complaints I see on HN are from people who
| know little about it, and are going off negative
| press/posts. Just as people knew little about modems and
| Linux. I mean, having to tell people "Don't give it
| access to your emails" is a clear sign of their
| ignorance. Kind of like having to tell someone "OK, just
| don't give your 10 year old the car keys" when they
| complain that cars are inherently dangerous because 10
| year olds can kill themselves driving it.
|
| It's worth trying it in a secure environment so at least
| one can make an _informed_ critique.
|
| Like you, I steered clear of OpenClaw, seeing all the
| problems and all the money people were burning on tokens.
| But at some point, I decided I should at least _try_ it
| in a safe way before rendering judgment. And now I see
| what it is. Has it done so much for me that I 'd throw a
| lot of money at it? Heck no. Not yet at least. But I do
| see we're past the point of no return. OpenClaw itself
| may die, but some derivative of it is going to be
| transformational.
|
| As I said: Make it secure, affordable, reliable and user
| friendly, and many App/SaaS services will disappear.
|
| > You don't need to use the technology to be affected by
| it. Ask Scott Shambaugh:
|
| > https://theshamblog.com/an-ai-agent-published-a-hit-
| piece-on...
|
| I don't know how old you are, but once everyone had a
| camera in their phones, the cat was out of the bag. Lots
| of people complaining about their photos showing up
| online because someone had taken a picture of them. Yes,
| this is bad. Yes, lives were lost (bullying, etc). And
| no, phones with cameras weren't going to go away. And
| everyone who complained has one now.
|
| And as I pointed out a few days ago[2], the whole Scott
| Shambaugh episode was pretty mild compared to what some
| open source maintainers have had to deal with when it
| comes to _humans_.
|
| [1] _Lots_ of cases where ISPs, etc kicked customers out
| because they were using Linux and they didn 't want the
| ISP to be implicated in criminal activities. "Only
| criminals use Linux"
|
| [2] https://news.ycombinator.com/item?id=47083686
| theshackleford wrote:
| > As I said elsewhere, complaining about this is like
| complaining that rm can let you delete your hard drive.
|
| rm won't wipe my HDD on a whim whilst instructing it to
| do something totally different.
|
| You pretending they are the same thing is disingenous.
| jcgl wrote:
| Sure, that's an interface that's better for many users and
| use-cases.
|
| However, it seems better if you could, as much as is
| possible, move the AI stuff from runtime to "compile time."
|
| Instead of having the AI do everything all the time, have AI
| configure your Zapier (or whatever) on your behalf. That way
| you can (ideally) get the best of both worlds: the
| reliability and predictability of classical software,
| combined with the fuzzy interface of LLMs.
| jbellis wrote:
| yes. in a similar vein, we're seeing that get standardized
| in coding agents as "don't have the agent use tools
| directly, have the agent write code to call the tools"
| skeledrew wrote:
| That's still too much work. Someone would have to make like
| an OpenClaw wizard that protectively offers to set all that
| stuff up. So the potential OpenClaw user can then, on
| running for the first time, be guided through the setup of
| whatever they'd like to get connected. And "setup" here
| means a short description of X and a "Connect? (y/n)"
| prompt. Anything more and you start losing people.
| BeetleB wrote:
| > Instead of having the AI do everything all the time, have
| AI configure your Zapier (or whatever) on your behalf.
|
| That _is_ what many use OpenClaw for! The AI assistant will
| happily recommend existing services and help you (or
| itself, if you let it), set it up.
|
| (In theory. In practice, it often does a poor job).
|
| The appeal of OpenClaw is I don't need to go research all
| these possible solutions for different problems. I just
| tell it my problem and it figures it out.
|
| Yesterday I told it to monitor a page which lists classes
| offered, and have it ping me if any class with a begin date
| in March/April is listed. This is easily scriptable by me,
| but I don't want to spend time writing that script. And
| modifying it for each site I want to be notified for. I
| merely spoke (voice, not text) to the agent and it will
| check each day.
|
| (Again, it's not that reliable. I'm under no illusion it
| will inform me - but this is the appeal).
| beepbooptheory wrote:
| Sometimes I reflect on all the metaphorical forests that have
| burned because a certain person at the right time only knew
| _so_ much about how to use Excel, or the inbox rules of their
| MUA, or being totally unaware of the incredible power of
| macros of all sorts.
|
| Like if you could just sit someone down for 30 minutes and
| show a few "power user" things, you will have truly taught
| her to fish for a lifetime. But it can go so unaddressed, and
| people's careers are built on these small ignorances.
|
| I've cancelled everything at this point and just call Emacs
| my "special agential assistant," it makes me still sound in-
| the-know, and most of the time no one knows the difference!
|
| "Convenience" in this context is laziness; "productivity" and
| "efficiency" is for management and bosses. We don't need to
| be our own bosses, I want to be _free_ from such things as an
| individual. I want to be capable, be maybe _almost_ "cool."
| Its sad to see a whole generation turn into such product
| dorks!
|
| "Oh please read my email for me Mr. AI!"
| chaostheory wrote:
| this reads like "I don't know why people are using instant
| messengers when you can just do SMS"
| recursive wrote:
| Apropos of nothing, I use SMS more than all the other instant
| messengers put together. It suits my purposes fine.
| Larrikin wrote:
| You're right that you probably don't need a notification to
| make coffee, but people are using it to create automations in
| Home Assistant so that it actually makes coffee for them.
| duggan wrote:
| I've heard it described as the first time many non-programmers
| have been able to make computers "do things" without it being
| defined by someone else (app interface, developer, etc). It's a
| hugely empowering development from that perspective.
|
| The stuff you've listed are the kinds of things smart home
| enthusiasts do with whatever tools are available to them, and
| are just a sign of people exploring the possibility space.
| jbellis wrote:
| are non programmers actually using openclaw successfully?
| because even "step 1 install your API keys" requires
| navigating concepts that are foreign to most "civilians"
| duggan wrote:
| Journalists, anyway. I think I originally heard it from
| Casey Newton on Hard Fork, but it was a month back so not
| 100% sure.
|
| But there's loads of people who would be stumped by a for
| loop, yet can easily work their way through a setup guide,
| particularly with the hype/promise and an active community.
| zingababba wrote:
| I dunno I gave mine root in a vps and am having it do security
| research, it's pretty sweet.
| simonw wrote:
| How much do you automate things in your life using Zapier and
| Automator?
|
| I know about those tools, and I'm always in the mood for
| automating thing... and yet I don't use them.
|
| I'm not yet running a Claw because of the prompt injection /
| lethal trifecta risks, but I absolutely understand the appeal.
| Reducing friction to automating stuff from "figure out
| Automator again" to "message your bot" is a material
| difference.
| WD-42 wrote:
| How much do you automate anything in your life at all? Seems
| like most daily drudgery comes from physical tasks. Feed the
| dog. Take out the trash. Personally I can't think of anything
| digital that could be automated that isn't already. I
| wouldn't be surprised if this the case for most people, with
| the exception of marketers and spammers which we are seeing a
| ton of adoption from with these tools.
| BeetleB wrote:
| I don't automate much because it's a pain.
|
| I have a desktop at home.
|
| When I'm at work, I often think of TODOs for home. I write
| them on a post it note, and then at home have to remember
| to add it to my TODO (no, I'm not going to manage TODOs on
| my phone - whole other conversation).
|
| I'll soon set up my Claw to be able to add TODOs (just add,
| not modify/delete). Then at work, I'll simply record a
| voice message to it telling it my TODO.
|
| Same goes for movies I want to watch, books I want to read,
| reminders, etc.
|
| I'm particular about the weather information I want (often
| want cloud cover percentage and precipitation probability
| for a set of hours). I couldn't find a good app on my phone
| that gives me this information. It was always a trip to a
| web site, modify some options, and hit Submit. Now I just
| ask my Claw and he has a skill for precisely my needs.
|
| Here's an analogy: I carry a Leatherman multitool wherever
| I go. People ask me why. They can't comprehend needing it
| often to make it worth the hassle. But now that I have it
| on me, I use the knife very often - several times a week.
| And I almost never reach for a screwdriver. But until
| you've had it on you for a while, you can't comprehend the
| utility.
|
| Back in 2005, lots of people asked "Why would I want a
| camera on my phone?"
| theshackleford wrote:
| > no, I'm not going to manage TODOs on my phone - whole
| other conversation
|
| I will. Far simpler, far more secure and far less
| wasteful than inserting some additional and unrequired
| LLM loop + hardware/virtualisation layer on top to do
| something I've already been able to do for years.
|
| > But until you've had it on you for a while, you can't
| comprehend the utility.
|
| You've not yet described anything that literally 99% of
| the population can not already do with the existing
| hardware and software in their pocket.
| BeetleB wrote:
| > Far simpler
|
| And far less capable. I have a whole system for managing
| TODOs, notes, etc, and I've not found an app that fits my
| needs (especially given that the system evolves over
| time).
|
| But I agree - if you have a flow that works great for you
| with just a phone, then I wouldn't recommend OpenClaw for
| that use case.
|
| > You've not yet described anything that literally 99% of
| the population can not already do with the existing
| hardware and software in their pocket.
|
| And in the early days, literally everyone I knew who
| owned an iPhone also owned a digital camera and a laptop.
| Why pay some crazy amount for a fancy phone?
| andrew_k wrote:
| Yeah, automation sounds good in theory, but you need to set
| it up, then it fails, and you need to fix the edge cases,
| maintain it. Even with OpenClaw, it still fails my daily
| briefing from time to time, and I keep debugging it, which
| isn't how I want to spend my time. At least with a bot I can
| keep asking it to "fix it"
| mjr00 wrote:
| > It also feels like people are automating things that don't
| really need to be automated at all (do you really need to be
| reminded to make coffee?)
|
| I've posted about this before, I call it the Jarvis effect.
|
| > For years we had people trying to make voice agents, like
| Iron Man's Jarvis, a thing. You had people super bought into
| the idea that if you could talk to your computer and say
| "Jarvis, book me a flight from New York to Hawaii" and it would
| just do it just like the movies, that was the future, that was
| sci-fi, it was awesome.
|
| > But it turns out that voice sucks as a user interface. The
| only time people use voice controls is when they can't use
| other controls, i.e. while driving. Nobody is voluntarily
| booking a flight with their Alexa. There's a reason every
| society on the planet shifted from primarily phone calls to
| texting once the technology was available!
|
| By and large the reason people love Openclaw is that it _feels_
| cool and futuristic. You have an AGENT! It 's DOING THINGS! Yes
| it's doing things you could have easily done yourself, but
| you're not doing them yourself, you have an AGENT! It's all
| very silly, the same way that having your lights controlled by
| your phone is very silly, but some people like it.
|
| That being said there a real use case for Openclaw, which is
| "marketing" (aka spam). A ton of people have set up Openclaw
| agents which exist to post on Twitter/Facebook/Discord/any open
| public user discussion forum (yes, HN included) to seem like a
| real member of a community, then start advertising something,
| generally crypto. So we can thank Openclaw for dead internet
| accelerationism.
| basch wrote:
| I'll disagree with you a little. The reason I don't use voice
| is because of context switching.
|
| With a mouse and keyboard I can switch windows.
|
| With my voice, the computer can't yet automatically determine
| if I am dictating a transcription or giving editing commands.
| What I really need is the interpreter listening to me to
| intuitively to know whether I am in the equivalent of VI
| command mode or insert mode.
|
| It is the roadblock to not needing a screen at all, right now
| I want to visualize whether it understood me correctly
| because if it didn't switch from insert to command
| automatically, I now have all my commands written into my
| paragraph. I also don't want to listen to the computer talk
| back to me to confirm it listened. I want to just keep going,
| to keep narrating my thoughts and trust it's doing the right
| things, not having to check. Having it slowly chime in to
| repeat that it listened derails my flow and train of thought.
|
| TLDR The future of voice is headless vi.
| skeledrew wrote:
| Problem I see here is you're trying to shoehorn a voice
| interface onto something that's highly optimized for
| keyboard input. The apps need to be redesigned to be
| accommodating of the interface, else it's just never-ending
| papercuts.
| basch wrote:
| That's what I'm saying. Voice as the input requires a
| completely new ui paradigm, and chat / chatbot isn't
| enough.
| mrguyorama wrote:
| Voice input will always be inherently worse than mouse
| and screen plus keyboard, because voice is linear.
|
| It can only ever be a linear sequence of input
|
| The 2 dimensional field of a screen and a mouse and
| keyboard give you extreme amounts of input and allow you
| to _contextualize_ that input in arbitrary ways that
| intuitively make sense to people with minimal training.
| Most people do not need to be taught that "Paste" goes
| to the active window.
|
| We barely even touch the surface of what is _possible_
| through this set of input devices and output and yet we
| can 't even get that level of fine grained and reliable
| control into touch screen devices and gamepads, let alone
| a linear stream of pitch.
|
| Voice cannot be a robust interface. It isn't between
| humans. There's immense nonverbal communication and human
| communication also relies very heavily on preshared
| context to actually get that info across in the first
| place. Even with all that machinery, human voice is
| generally considered to only carry, regardless of
| language, 44ish bits per second of data.
| jredwards wrote:
| And this is how you get Moltbook.
| jasonkester wrote:
| Interestingly, your example is an actual thing we used to
| have.
|
| In 1996, I picked up the phone on my desk, dialed a 3 digit
| code, said "I need to fly to Los Angeles on Tuesday morning,
| returning Wednesday evening". A couple hours later, an
| envelope appeared in my inbox with plane tickets, rental car
| reservation and hotel reservation.
|
| Then every company in the world fired all the secretaries
| over the course of the next few years to cut costs, and we've
| collectively forgotten that it was ever like that.
| mjr00 wrote:
| Your example is a great example because the secretaries are
| clearly filling in the gaps, such as
|
| 1. How much can you spend on this trip? 2. Is
| first/business class necessary? 3. Is a layover acceptable
| if it's cheaper? 3a. Is it better to have a 4am flight
| nonstop or a 7am flight with a layover? 4. Are there
| preferred airlines? 5. Are there preferred hotel chains?
| What's the hotel budget? Do you want to pay extra for a
| nice view? 6. What kind of car should you rent? Is there
| equipment you'll be handling?
|
| etc...
|
| This is the kind of stuff that's easy(-ish) to communicate
| by presenting a list of options to a user through an actual
| interface. It sucks doing it through voice; think of the
| old phone systems where you had to go through droning "If
| you would like to rent an SUV, press 1. If you would like
| to rent a sedan, press 2. To speak to an operator, press
| 0."
|
| So no, you never had a voice interface for booking flights;
| you had a human brain to whom you delegated, which is very
| different.
| zahlman wrote:
| > (yes, HN included) to seem like a real member of a
| community, then start advertising something
|
| Ah, so that is indeed the endgame of what I've been seeing,
| hmm?
| joshmn wrote:
| > I keep reading folks saying OpenClaw has completely changed
| their life while posting a picture of 58 mac minis on their
| desk.
|
| I was having a conversation with someone about OpenClaw, and
| they proposed this idea of OpenClaw being used for inventory
| tracking at the retail-level. I let them continue. They said
| it'd be the best option for tracking when purchases are made
| and what SKUs are sold at what time of day. They weren't
| talking about prompting, they were talking about it as a data
| store.
|
| I didn't bother mentioning how long this problem had been
| solved.
|
| It's not you being a curmudgeon.
| 9cb14c1ec0 wrote:
| I've long thought it would be funny to do a startup where we
| would make accounting software that was solely a chat
| interface, with the only data store being a GL account list
| stored in context. There is probably a VC firm dumb enough to
| fund it.
| RHSeeger wrote:
| > I didn't bother mentioning how long this problem had been
| solved.
|
| The ironic thing here is that the person could go to ChatGPT
| (or whatever), describe the problem they're looking to solve,
| and ask it to find them the various ways it has been solved
| reliably (with links to the sources to confirm the
| information). And even provide some details on when each
| solution works best and why.
|
| Because THAT is a great use for AI.
| skeledrew wrote:
| They could do that, but then they'd have to then do the
| actual legwork after, whether that means finding the
| proposed solution or whatever (after maybe glancing at a
| few of those pesky links), installing and configuring it.
| What OpenClaw represents is the ability to, in natural
| language, state what you want and then take off with the
| assurance your will will be done. Just as you'd expect when
| tasking a human assistant.
| jokethrowaway wrote:
| The only useful use cases I've heard about are all about
| automating using horrible websites with horrible interfaces.
|
| Eg. tell it to book a flight ticket for X without dealing with
| "modern UX" and 1GB websites
| Anon1096 wrote:
| Can't believe that I haven't seen the obvious answer, that
| OpenClaw is simply more fun to use. Sure, you MAY be able to do
| what OpenClaw does through 5 other dedicated tools, but you are
| going to take way longer to do so with a ton more drudge work.
| And above all else: it is extremely enjoyable to talk to the
| computer in normal language and just have stuff happen. And
| it's got a personality that you can tweak to your liking.
| Personally it's the most fun I've had using a computer in a
| long time.
|
| IMO OpenClaw or a similar agent will be on everyone's phone in
| a couple years. It's basically what Siri was always supposed to
| be. For the average user it's obvious that this is the way
| computers are meant to be interacted with.
| rubslopes wrote:
| My experience also. I could manually connect my Obsidian
| notes to my AI, sure, but what I did instead was writing
| "Obsidian just released a CLI headless sync tool, install it
| so we can use it" and in a minute it came back with "Ok,
| everything installed, I just need your login and password."
|
| Dangerous? Yes, very, but it truly feels like living in the
| future. Surprisingly, it's even more fun that sci-fi movies
| made me think this would be.
| 0x457 wrote:
| OpenClaw in most cases also going to use the very same
| dedicated tools, maybe variation of those tools dumbed down
| for LLM.
|
| Almost every time I have an idea for AI Agent, I end up just
| making a script/binary that does the same, but so much faster
| that adding AI to it feels silly.
|
| Recently I made a tool router that runs locally for such
| tools. Some tools have no arguments at all. Claude created a
| quick overlay where I can text/speak, and it will do tool
| call, without me asking for it, Claude added 4 buttons next
| to text input that bypass agent and just do a "tool call". I
| barely use text-to-command because those 4 buttons cover 9/10
| of my use cases.
|
| At this point I'm trying to come up with tools to add to it,
| so it's actually useful as an agent. Almost everything ends
| up being a cronjob or webhook triggered thing instead.
| sethjgore wrote:
| Can you give an particular example?
| rockbruno wrote:
| When the AI companies run out of money, I predict tokens will
| stop being dirt cheap and such setups will become extremely
| expensive (even for regular software engineering to some
| extent). Then it's become clear how over-engineered most things
| we do with AI are
| patrickk wrote:
| In parallel, local models are getting better and better, so
| eventually they'll get "good enough" to run fairly cheaply at
| a level close to the current Sonnet/Opus models (what I run
| Claudeclaw with), on Groq, Openrouter or whatever commodity
| provider. Perhaps even mid to high end consumer PCs when the
| current RAM madness subsides.
|
| There's loads of good discussions about local LLMs in this
| thread:
|
| https://news.ycombinator.com/item?id=47190997
| skeledrew wrote:
| > tokens will stop being dirt cheap
|
| That can't be allowed, and also won't happen. If token costs
| do start going up at a serious rate in the US, you can be
| sure that they'll stay down in China, and the political
| situation won't allow for the inevitable exodus to Chinese
| providers.
| siva7 wrote:
| The old dudes had something they called the "Eternal September"
| like when ISPs began providing free internet access and
| discussion culture declined after forever. I starred this
| thread here as the start of the "Eternal March" when the open
| internet died forever.
| rcxdude wrote:
| It was more that regular people started joining the internet
| through just paying for ISPs. Before that, most of the people
| just joining the internet were students, so there would be a
| wave of newbies at the start of the university year every
| September and they would get acclimatised to the culture
| there during the year. But once it was year-round and many
| more people it swamped things and the culture shifted or
| closed itself off.
| Sharlin wrote:
| Exactly. The "September" was an existing phenomenon, but
| was only limited to a couple of months every year. It
| became "Eternal" after the masses started finding their way
| to internet (well, USENET in particular).
| 2OEH8eoCRo0 wrote:
| We also have _No Silver Bullet_ from Mythical Man-Month
|
| https://en.wikipedia.org/wiki/No_Silver_Bullet
| collingreen wrote:
| September was part of the metaphor because it was a time when
| decent internet access was mostly via universities and
| September was when the new batch of freshmen "came online"
| and started stumbling around the places these folks were
| regulars at but eventually assimilated or left before the end
| of the school year. (I expect the same thing happens at the
| bar scene in college towns but I've never heard it described
| that way.) Eternal September is the forever version of
| everyone having access and overwhelming those spaces without
| it ever being able to recover.
|
| Is there something I'm missing about March or is it just a
| diverging reference? If the wave of non technical folks being
| able to automate new things is here, what's the equivalent
| impact of that? Maybe this is the inflection point where
| everyone needs more tech support like some sort of post
| Christmas surge? Maybe less because they have the tools to
| help themselves without trying now?
|
| I'm not sure we're there yet anyway; I think this is still
| first adopters and enthusiasts. I asked my wife and some non
| technical friends and none of them have heard of openclaw
| yet. I think the deluge will happen if Apple or Android bakes
| it in or one of the big ai companies makes the app good
| enough for a normal person to unleash it upon their life and
| community.
| iceflinger wrote:
| Eternal March already happened in 2020.
| jasonshen wrote:
| Many breakthrough technologies appear initially like toys. And
| this certainly qualifies. I've never been able to code anything
| more complicated than a memory game in javascript but I have
| worked with engineering teams for my entire professional
| career. But prompting my agent to write python scripts to pull
| down data from various tools via API without having to read
| docs, do trial and error for hours / days / indefinitely, and
| actually produce something coherent in seconds? Incredible.
|
| Is my OpenClaw agent currently changing my life? No. It sends
| me a morning briefing based on my calendar, the weather, my
| Readwise highlights, and notes on who I'm talking to today
| based on call transcripts. I use it as a food diary (which I
| could have done on platform LLMs but this feels like a more
| personalized UX as we can write the logs to text files on my
| personal computer). I can absolutely see how transformative
| this agent can become in the next few years. Certainly my usage
| of LLMs has changed my life since ChatGPT first launched.
|
| You are seeing the loudest / most hyped users. There's a reason
| it has so many stars and most of the people getting something
| out of it are not posting on X. They're just using it to do the
| thing.
| blenderob wrote:
| > There's a reason it has so many stars and most of the
| people getting something out of it are not posting on X.
|
| That reason is buying stars, agent swarms, and astroturing.
|
| No project gathers 200K stars genuinely in 3 months. There
| are far more useful and popular projects that need 10 years
| to get 200K stars. When you see a project like this get 200K
| stars in just 3 months, you know something is very fishy.
| skeledrew wrote:
| Or you're just missing the generally wide appeal of the
| project.
| Sharlin wrote:
| There just aren't enough hobbyists in the world running
| local AI models, never mind technically savvy enough to
| hack something like OpenClaw _and_ be really excited
| about it.
|
| For a comparison, the local image gen interfaces ComfyUI
| and A1111 WebUI have a huge amount of stars (~100k and
| 160k respectively, accrued since 2022 or so), but they
| allow you to _create porn customized to whatever kinks
| you have_ , not just automate things for the sake of
| automation. One of those is a rather bigger value prop
| than the other, dopamine-wise.
| LanceJones wrote:
| There's no need to run local models with OpenClaw. I use
| Anthropic's oAuth Max20 Plan subscription via their
| SDK...
| kaashif wrote:
| I bet if people could star repos anonymously those porn
| repos would have more stars.
| tmp10423288442 wrote:
| Why would they be running local AI models? The creator of
| OpenClaw explicitly recommends against running OpenClaw
| using local LLM models at this time, because they're not
| as powerful as frontier models as well as much more
| gullible to prompt injection and the like.
| adampunk wrote:
| Yes, you're right. It's the children who are wrong.
|
| Why is it so difficult to imagine that something that looks
| popular and fun is popular and fun?
|
| Also, really who is paying for stars on open claw? Who
| benefits here?
| Xirdus wrote:
| Do you have any examples of 20th or 21st century breakthrough
| technologies that started out as toys? I can only think of 3D
| printers.
| DomB wrote:
| Drones
| kilroy123 wrote:
| It's been utterly bizarre to witness. I've used n8n for years
| and told everyone who would listen to give it a try, well
| before LLMs. Same for huginn the open source project.
|
| I just don't get all the hyper either. I think it's because
| people just create automation workflows by typing them out
| rather than being in the trenches.
| steve1977 wrote:
| A lot of it certainly looks like a solution in search of a
| problem.
| dg2fgfg wrote:
| https://www.youtube.com/shorts/PGjueA3FLIQ
|
| Im really not sure why this has to be said again and again..
| it seems humans just don't learn do they?
|
| Im waiting for someone to show me something that starts with
| the experience and then explains how the LLM fits in. Not the
| other way round.
|
| I think because Google Search is predominantly tech-based, it
| is easy to see why LLMs have impacted the way we think about
| the experience associated with Search over large spaces of
| information.
|
| Beyond that, Im not seeing much.
| Gooblebrai wrote:
| This comment could be on its way to http://hackernews.love/
| SunshineTheCat wrote:
| Not sure if you read the headline on that site, but it says
| "bad idea."
|
| I never said OpenClaw was a bad idea.
|
| I said the way most people are using it now isn't practical
| and/or saving them any time, and if there were ways, I would
| love to hear about them.
|
| This is part of why the whole discussion has been so low
| value: people always default to "yep you're going to be
| proven wrong one day" or "you'll just be left behind then"
| instead of showcasing an actual, real life, practical example
| of using it to be more productive.
|
| If you think it's fun and enjoyable, then have at it. I'm
| just not the biggest fan of people wasting a bunch of time on
| novelty and then telling me I'm dumb for not doing the same.
| lenwood wrote:
| I agree with the majority of your comment. I haven't yet found
| a use case to justify running this myself. I did find one use
| case that impressed me though. There's an OpenClaw agent that's
| actively answering questions on the #help channel of their
| Discord server[1]. So I asked it a question as I was getting
| started. It answered in < 2 mins with a detailed explanation of
| my issue, how to fix it, and asked relevant questions to guide
| me. The answer was better than I received from Claude or
| Gemini. I'm still not sure if I personally need OpenClaw, but
| the Krill bot offers pretty great support. I would be curious
| to know what it costs them to provide this.
|
| [1] https://discord.com/invite/clawd
| vmbm wrote:
| I think a lot of the hype is coming from content creators who
| are actually finding it useful for content creation. Generating
| ideas, organizing notes and research, writing scripts and
| articles, managing schedules, editing, promoting, etc...
|
| I assume a lot of these folks were already using LLM's quite a
| bit, but were using the Chat interfaces or had workflows that
| were split among a bunch of different services and tools.
| Something like OpenClaw gave them a way to centralize a lot of
| that and also gave them a way to use natural language to direct
| efforts. So for them this probably feels like a big step
| change.
|
| If you are coming from a programming background you were aware
| that this type of setup has been doable for a while, but you
| were probably content sticking with Claude code or similar
| tools because those tools covered most of your LLM based
| workflows quite well.
|
| And tying this altogether, one of the lowest hanging fruits for
| content creators is to create content about the tools they are
| using. Doubly so if that particular tool is starting to go
| viral. So you end up with a self feeding virality of sorts, as
| OpenClaw got more popular, more content creators started using
| it, and then publishing content about it, etc....
| Volundr wrote:
| What I find crazy is the sheer amount of access and trust
| involved in these LLMs. Every time I think about something I
| might like to do with it, I think about the amount of damage
| the LLM could do, e.x. even with read only access to my email
| combined with Internet access, and nope out. It's wild to me
| anyone trusts these things unsupervised.
| mgraczyk wrote:
| And yet they didn't do that!
|
| Really makes you think about what makes products good
| BeetleB wrote:
| > But every single use case I've read so far could be done with
| a pretty affordable SaaS product, Zapier, Automator (app on a
| mac that's existed for over a decade),
|
| I don't want to learn N different SaaS products (nor worry
| about them changing their TOS, going away, etc).
|
| To be blunt, if OpenClaw were reliable, secure and affordable,
| lots of SaaS products would simply die. Why spend the time
| learning all of them when I can just tell the assistant what I
| want?
|
| > or something simple you could make yourself.
|
| That _is_ OpenClaw at a higher abstraction! Instead of me
| sitting typing, or babysitting Claude Code, I can just tell
| OpenClaw what I want and it makes it for me.
|
| (When it works, that is).
| rush86999 wrote:
| Everyone is using OpenClaw for personal productivity, but
| you're right. Not much value, as you can get that from existing
| products.
|
| The market will eventually realize the business case for an
| OpenClaw-like product, and I'm waiting to ride its coattails!
|
| https://github.com/rush86999/atom
| m463 wrote:
| > But every single use case I've read so far could be done with
| a pretty affordable SaaS product,
|
| reminds me of those "zune already does everything ipod does"
| posts.
| teg4n_ wrote:
| The iPod came out way before Zune.
| pclark wrote:
| Ok, I'll bite and run the HN skepticism guantlet.
|
| I have an OpenClaw setup with a Claude API token and Qwen local
| model, running on an M4 Mac Mini with 32GB RAM.
|
| 1. At 7AM and periodically throughout the day it checks my
| calendars (work, parenting schedule, personal), a hyper local
| weather station, and some specific news topics -- and sends me
| a summary and throughout the day updates if anything
| significant happens.
|
| 1b. It also sends this to my TRMNL e-ink display.
|
| 1c. It can also add and edit calendar invites, so if I want to
| move my yoga I can just tell it to move it to whenever the next
| yoga class is at (it knows what studio I go to and figures it
| out)
|
| 2. It has a skill I built that acts as a second brain for
| knowledge. I can send it Fitness Youtubes, parenting/health
| research papers, podcasts -- and it organizes, summarizes and
| saves it in a logical file structure. Then in the future I can
| access these. It's like bookmarks on steroids. I love it for
| 1-2hour YouTube videos where I want summaries. It also pulls
| out any books any artifacts mentions and generates me a rolling
| reading list. https://plc.vc/npw
|
| 3. It has its own email address -- and read access to my
| personal email -- so friends can email it to schedule things
| like evening video game sessions. Similarly, if I get an urgent
| looking email it'll provide it in #1. I don't check my personal
| email aside from via OpenClaw.
|
| 4. It has read/write access to my GitHub, and each project repo
| I have has a well defined Claude structure, so it can make
| changes, commit the branches to Fly.IO and send me domains to
| test things. I love it for esoteric tweaks to my blog.
|
| 5. It has access to my Apple Reminders so I can message it
| things like "remind me to buy more muffins" and it has context
| to know to add those muffins to my Costco grocery list not
| Trader Joes.
|
| 6. It runs a headless browser, so when my hyper local weather
| service (Bouldercast) sends a summary that has more detail
| behind a login, it can open the email, click the link, login
| with my credentials, summarize the forecast, and send it to me.
|
| 7. It drafts blog posts for what it did for me each week. It's
| fun! https://plc.vc/d5t
|
| I am a previous Zapier power user. I have used their LLMs,
| databases and Zaps extensively for the past decade. I
| understand the scorn towards AI, and I understand that if you
| look at this list you might think that it's either trivial
| tasks and/or things that could be done with Zapier, but I have
| been _amazed_ at how effortless it is to setup.
|
| Similarly, I love that I can on the fly improve this assistant
| -- last night I told it "I want to extend our Knowledge skill
| so that you can subscribe to RSS feeds and summarize articles
| in my knowledge base and also deliver interesting content in my
| daily summaries. Update the knowledge skill and our tasks to do
| all this."
|
| It one shotted that, simply asking me to provide the first RSS
| feed I wanted to subscribe to.
|
| It's genuinely like having a human assistant that happens to be
| an expert coder/technologist on call 247 that works at the near
| speed of light.
|
| It disappoints me that technologists are so skeptical of this
| technology rather than exploring what it is and why it might be
| different to what exists today. It's fun! thats the takeaway:
| it's FUN.
| adampunk wrote:
| It's really not rocket science.
|
| Like other people have said people are having fun with their
| computers; that's why it's popular. That's also why a bunch of
| people on forums throwing their hands up and saying "I don't
| understand it. Why don't they see that there shouldn't be any
| fun whatsoever?" is not really a deterrent at all.
|
| It's also why it doesn't matter that the categories of tasks
| they are doing can also be done with a whole set of tools that
| are no fun to use.
| xnx wrote:
| Normal people use speakers to listen to music. "Audiophiles"
| use music to listen to their speakers.
|
| This applies to *clawphiles just as accurately.
| fidotron wrote:
| What's so incredible about OpenClaw is so much of the value
| people are deriving from it relates to: cron jobs, remote access,
| "privacy" (which really it's not if using remote LLMs) and an
| inability to fuse data across siloes by normal people, so relying
| on AI to do it.
|
| If we had a decent technical universe much of this stuff would
| work in ways that simply don't require LLMs for anything other
| than the initial setup.
| brtkwr wrote:
| I got OpenClaw to compile Node from source on my old Jetson Nano
| so that I can run OpenClaw natively instead of using Bun. It took
| 30 hours but it did it by spinning up a tmux session for the
| build and using a cron to monitor the tmux pane every hour and
| even fixing a failure at 5 am which I would have had to find out
| later had crashed but it had actually found what needed to be
| changed for the build to continue and it continued building....
| Now I have the latest version of OpenClaw running on Node 22 on
| my 5 year old Jetson Nano running Ubuntu 18 which I cannot
| upgrade. What they say is all true, it is incredible stuff when
| it works!
|
| Full story: https://brtkwr.com/posts/2026-03-02-upgrading-
| openclaw-to-la...
| rune-dev wrote:
| Apologies if I missed it while skimming your blog post.
|
| But could you estimate the token cost of this? Or were you able
| to comfortably do this with a subscription plan?
| brtkwr wrote:
| Yes, it skimmed the tmux pane every hour and well within my
| Gemini free tier.
| rune-dev wrote:
| That is impressive! Thank you for sharing
| brtkwr wrote:
| I just mentioned it in the blog post to flag that it
| doesn't come for free :)
| bombela wrote:
| That's really cool.
|
| But wouldn't have been quicker and simpler to add ".bun/" to
| the pattern of authorized paths the same way it presumably
| works for ".npm/"?
| brtkwr wrote:
| It didn't survive OpenClaw upgrades unfortunately, it ended
| up killing my OpenClaw gateway when I asked it to self
| upgrade. Bun is marked as an experimental package manager and
| the recommended way to run OpenClaw gateway is node so I
| wanted to do it properly. I would have liked Bun to be
| supported property. I'd raise a PR against the repo but
| looking at the 4.5K open PRs, it doesn't give me much hope
| about it ever getting merged.
| skeledrew wrote:
| Seems to have been addressed in the article:
|
| > Starting around OpenClaw 2026.2.26, the project tightened
| plugin manifest validation. Manifests outside expected trust
| boundaries are now rejected as unsafe. On my Jetson, Bun's
| global install layout
| (~/.bun/install/global/node_modules/...) tripped those checks
| for every single plugin
| Tadpole9181 wrote:
| What do you mean "run OpenClaw natively", you're just running
| Node?
|
| I'm also curious if it's particularly wise to have a web-facing
| system running on software that hasn't had a security update in
| 3 years?
| brtkwr wrote:
| Yes sorry about the confusion, I meant "the recommended way"
| rather than natively
| xantronix wrote:
| It's bizarre to me how Microsoft somehow owns two of the largest
| social networks for software developers.
| ChristianDavis wrote:
| Oh look, another public service being looted for nefarious
| purposes. Thanks OpenAI!
| DeathArrow wrote:
| OpenClaw agents are starring OpenClaw project? What a surprise!
| neals wrote:
| Gives me mongodb vibes. This whole Ai coding thing too. On one
| side, religious loud following, on the other side the nay sayers.
| We'll probably end up in the middle.
| cpursley wrote:
| Fwiw, Claude and Codex are very very good at SQL and have
| actually taught me some new tricks. No reason to use mongodb or
| firebase in 2026: https://postgresisenough.dev
| tym0 wrote:
| Did an AI write this? Completely missed the point ^^'
| dsr_ wrote:
| CocAIne is a hell of a drug.
| informal007 wrote:
| Is there a place to show what users use OpenClaw in life or work?
|
| I've tried OpenClaw two weeks but don't know what it can do for
| me.
|
| I let it to finish some project for me, but the most hard work
| for project is validating the results over giving instructions
| r0b05 wrote:
| So React was the last most human-starred project on GitHub before
| the dawn of agent-starred projects.
| hinkley wrote:
| I say, 'your civilization' because as soon as we started
| thinking for you, it really became... our... civilization.
| blueTiger33 wrote:
| just gave a star to Linux
| toinewx wrote:
| I tried it today for the first time. The onboarding is okay.
|
| I picked Whatsapp but it ended up using my own account! So it's
| absolutely too dangerous. We are supposed to create a separate
| account but with which phone number? I only have one.
|
| So I picked Telegram instead, added it to a group chat, but it
| was a slog to set the authorizations.
|
| In the end I don't trust it to read my mails for security reasons
| so I uninstalled it!
| AbraKdabra wrote:
| > I picked Whatsapp but it ended up using my own account! So
| it's absolutely too dangerous. We are supposed to create a
| separate account but with which phone number? I only have one.
|
| You're joking right?
| toinewx wrote:
| nope, they recommend creating a separate whatsapp account.
| but fall short of saying you need a separate number (and
| subscription)
| recursive wrote:
| What would the joke be? I haven't touched OpenClaw and
| probably won't. I use WhatsApp lightly, but it seems like it
| requires a distinct phone number, used as an account
| identifier. So for the benefit of those of us not immersed in
| this scene, could you elaborate?
| AdamN wrote:
| MacOS supports multiple users - I would absolutely sandbox any
| agent like this and only slowly give it permissions (and never
| to anything that's critical without compensating controls).
| eddof13 wrote:
| I'm tempted not to use it to control everything, but install it
| on my mac and give it access to keyboard maestro macros and
| that's it
| TrackerFF wrote:
| Wonder how much of that is contributed by bot/farm accounts. The
| creator certainly has the means. EDIT: I should mention, I'm
| talking about the initial growth / traction.
| dokdev wrote:
| Github stars started feeling more and more meaningless every day.
| nkzd wrote:
| I am yet to see one good use case for it.
| amelius wrote:
| When I ask ChatGPT about OpenClaw, it refers to:
|
| https://github.com/pjasicek/OpenClaw
|
| OpenClaw - Captain Claw (1997) reimplementation
| maybeiambatman wrote:
| Great game.
| sva_ wrote:
| ... It was mostly starred by OpenClaw Bots Agents, wasn't it?
| hmokiguess wrote:
| Who are these people? I was skeptical at first and seriously
| thinking surely not the software engineers out there as we see in
| HN how risky and wild this is. Then, to my surprise, a coworker
| came and told me they were running it and happy with that setup.
| I was baffled, but I work with Gen Z in a pretty niche Gen Alpha
| market, so I kinda feel like they're somewhat more likely to go
| for these things. What's your experience?
| sva_ wrote:
| > Who are these people?
|
| For example, someone working in safety and alignment at Meta:
| https://nitter.net/FakePsyho/status/2025857836014538818
| g947o wrote:
| That kind of explains why Meta's AI effort has been going so
| well for the past year.
| hmokiguess wrote:
| Mixed feelings here, if she is a researcher then I guess part
| of her research should be explore this in some level of depth
| with real stakes. Though this does make it seem like that was
| not what she was doing there.
| ffsm8 wrote:
| If I could use it at my day job, I'd do it within a heartbeat -
| albeit only with readonly access (with write only on it's own
| files/output/sandbox)
|
| There are so many mails and communications with so many tasks
| to research via confluence etc
|
| But on my private hardware? Idk, I haven't found a use for
| it...
| hmokiguess wrote:
| I'm sure you can already do some kind of scripting + LLMs
| without necessarily needing this at your work though, no?
|
| Email is stored in your device somewhere, you could just get
| its content sent to your preferred agent, you can use one of
| the many mobile clients if you rather interact through that
| kind of UX (like self hosted hapi.run + tailscale for
| example), and you could setup a cronjob or something like it
| on your machine to do it based on whatever interval. This is
| just one way I personally could go about it, YMMV obviously.
|
| Is there a specific reason why you will not do something like
| that for example?
| croddin wrote:
| As many other comments have said there probably is a good percent
| of stars by claws themselves, I would be curious what percent
| this is but it is also interesting: current "dumb bot" stars/spam
| etc is entirely automated and coordinated but these claws
| probably independently reasoned over long thought chains about
| why it is a good idea to star openclaw.
| ivanjermakov wrote:
| GitHub star count was a good metric until it became clear that it
| is a good metric.
|
| https://en.wikipedia.org/wiki/Goodhart%27s_law
| blenderob wrote:
| Look at the graph - https://api.star-
| history.com/svg?repos=facebook/react,opencl...
|
| React and Linux got their 200K stars slowly but surely over 10
| years. OpenClaw got their 200K stars in like 3 months! Is this
| any meaningful comparison?
|
| Getting 200K stars today doesn't mean much because today stars
| can be bought. There's a big shady thriving business of selling
| stars. Stars today can be generated using swarm of thoughtless
| agents. What's the use of counting these stars when they don't
| mean anything anymore?
| crumpled wrote:
| I agree with your point, and am only responding to the last
| sentence.
|
| Starring can be useful to the starer. They are just counted
| because it is countable. Whether you find the number meaningful
| remains up to you.
| ASalazarMX wrote:
| Besides, stars != installs, these days they're a popularity
| contest at the level of Facebook likes, not a measure of a
| project's success.
|
| Let's wait for the explorers to return.
| mikey_p wrote:
| Who cares about stars on Github???
|
| "If dev null is fast and webscale I will use it"
|
| "Does dev null support sharding"
|
| Who remembers https://www.youtube.com/watch?v=b2F-DItXtZs
| croddin wrote:
| In other news, "Show HN: This up votes itself"[1] from 14 years
| ago is still the 20th most voted story in HN history.[2]
|
| [1] https://news.ycombinator.com/item?id=3742902 [2]
| https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
| iJohnDoe wrote:
| I have a strong hunch that everything regarding OpenClaw is pure
| guerrilla marketing. If so, the only thing amazing about OpenClaw
| is their wildly successful marketing campaign.
| draxil wrote:
| how many of these stars were applied by openclaw?
| mikeocool wrote:
| This sort of highlights the meaninglessness of GitHub stars?
|
| React has been around for over a decade, and in that time pretty
| significantly impacted web dev paradigms (along with a few other
| mediums).
|
| It's hard to imagine being a web developer today and not knowing
| at least some react.
|
| OpenClaw has been around for like a few months? And maybe it's on
| its way to having that sort of impact? But right now seems to he
| mostly the purview of very early adopters and AI influencers.
| tantalor wrote:
| It's basically the same as _The New York Times Best Seller
| list_
| Tadpole9181 wrote:
| GitHub accounts are free and the project is literally a bot-ing
| service. It stands to reason that the tens of thousands of
| robots unleashed on the web are responsible for these stars?
|
| It's larger than literally every open source service I thought
| to use as a benchmark. Rust, React, Vue, Symfony, Laravel, PHP
| Stan, Python, ESlint, rails, LLVM, Spring, _fucking Linux
| itself_.
|
| I would wager the legitimate stars for OpenClaw are single
| digit percents of this. But hey, I haven't actually run the
| numbers on the GitHub API.
| ramoz wrote:
| OpenClaw is not going away anytime soon. And I don't think it can
| be platformed behind web UIs. OpenAI owns an OS with this one.
|
| I avoided the hype at first; however, it has become extremely
| efficient for emails and notes, and I can see how this can extend
| to any sort of digital workflow. The convenience of chatting with
| this thing, no matter where I'm at, is a key marker.
| ramesh31 wrote:
| Stars have become completely meaningless in the last year or two.
| It's a shame, because having a few thousand Github stars used to
| be a really big deal, and was a quality marker for libraries that
| had reached a level of maturity and production grade. Now it's
| just social media bot driven nonsense.
| cfiggers wrote:
| It's entertaining to me to imagine future historians arguing with
| one another, writing dissertations, publishing virtual reality
| eyeBooks, explaining to one another all about the ancient
| etymological connection between "claws" and "webhooks".
| faize wrote:
| I spent around $5 setting up a small bot and sending a few
| requests through the Claude API.
|
| For those who use Claude (or similar LLM APIs) on a daily basis,
| what does your monthly spend look like in practice? And do you
| feel the cost is justified by the value you're getting?
| skeledrew wrote:
| I got the full value of my Claude Pro subscription in the first
| couple few hours of having taking the leap. Hit the message
| limit and had to edit for reset, but I was already a happy
| customer given the progress I made on a project that I was
| trying to recover (couldn't quite figure what was needed to get
| it ready for real world usable, but Claude Code figured it and
| it was a good collab getting it there).
| LanceJones wrote:
| $200/mth USD for me. Anthropic's oAuth Max20 subscription via
| their SDK. I've had several 100M+ token days without even a
| blip.
| 4dregress wrote:
| I had no idea what openclaw was, just checked and no thanks I'd
| rather do all that stuff myself.
|
| Why are people so keen to let a company get that close to their
| real life's, it's terrifying!
| melonpan7 wrote:
| Half of them coming from agents
| DrammBA wrote:
| I've seen multiple comments saying that openclaw stars itself
| during onboarding or that it asks its user to star, but noone has
| posted any proof, is there any concrete evidence for those
| claims?
| singularity2001 wrote:
| Am I blind or does this post not contain any links to the GitHub
| in question???
| throwaway13337 wrote:
| The stars are probably legitimate.
|
| It's weird that most people in these comments are speculating
| fraud.
|
| Why aren't companies with real money to gain from stars gaming
| the system to the same degree? Why do the other metrics - issues
| and pull requests - match up with its popularity? Why would the
| bots starring the repo mean that those same bots are not popular?
| Those bots are controlled by their users.
|
| The project is extremely active because this is what everyone
| being able to customize their computing looks like. A mess.
|
| But it's a good mess.
|
| Github was the old code sharing model clearly not designed for
| this. I'm sure a new model for code sharing will come to fix the
| growing pains.
|
| A ton of people who would have never been able to customize their
| computing experience are finally able to. And it is magical for
| them.
|
| This means that those same people will finally value having
| access to source and use of open protocols.
|
| It was always valuable to us because we had the power to make it
| matter. It never mattered to them because they did not. Now they
| do.
|
| The last era of computing was defined by dumbing down computing
| for the masses. Less information, less customizable, and more
| metric driven. Control in the hands of the companies.
|
| This new era will look more free/libre, more personal, and less
| enshitified. Control in the hands of the users.
|
| This is a very positive development.
| echoangle wrote:
| > Why aren't companies with real money to gain from stars
| gaming the system to the same degree?
|
| How are you gaining money from stars? Why would Facebook bot
| stars for the react repo?
| butz wrote:
| So, how do I use this OpenClaw to automate actually useful
| things, like sweeping floor, washing dishes and doing laundry?
| recursive wrote:
| Give it one of those tesla bots.
| throwyawayyyy wrote:
| A lack of imagination on my part perhaps, but I can't think of
| anything I'd use it for which isn't either: 1) cheating myself
| and others of leisure (e.g. I suppose I could use it to fake-
| keep up with friends..? Or plan a holiday and book a load of
| stuff for me. But I like doing that!), 2) not feasible (loading
| and unloading the dishwasher, which is already the robot I used
| to wash dishes), 3) utterly insane (it's tax time in the US).
| m463 wrote:
| Maybe AI is helping with the difficulties of upvoting a project
| on github.
|
| or is it tooting its own horn?
| johnwheeler wrote:
| I wanna understand this, but it's gone from a bunch of people
| talking about how great it is to a bunch of technical people
| talking about how worthless it is. So I think it's probably not
| that great. Who cares if I can chat remotely with my AI? What's
| the difference?
|
| What's so good about that?
| deafpolygon wrote:
| How much of it is AI agents starring the project?
___________________________________________________________________
(page generated 2026-03-02 23:01 UTC)