Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claws are now a new layer on top of LLM agents

twitter.com

Post reply on HN
Print view View original

811–820 of 1001 posts

Re: Claws are now a new layer on top of LLM agents

#811

Post by RamblingCTO »

kristopolous wrote: post #798
corndoge wrote: post #746

I still don't understand what openclaw is or does and i've read the docs multiple times over. "Any OS gateway for AI agents across WhatsApp, Telegram, Discord, iMessage, and more. Send a message, get an agent response from your pocket. Plugins add Mattermost and more." "What is OpenClaw? OpenClaw is a self-hosted gateway that connects your favorite chat apps — WhatsApp, Telegram, Discord, iMessage, and more — to AI c…

it's the 40th or so implementation of an old idea but it's the one that was done when the models got good enough to make it useful by someone who goes on podcasts. [1] Just like youtube was the 40th or so online video site but it's the one that was done by members of the paypal mafia and when enough people had high speed internet. and that is literally it. You can do that right now. Go through the 2023 LLM-related pr…

So creating skills/MCP servers itself and basically change its own nature is not a new thing? Clawdbot was the first were it worked really well. So I'm not sure you actually used and experienced it? Cynical comment is what it is.

Re: Claws are now a new layer on top of LLM agents

#812

Post by mr_mitm »

aqme28 wrote: post #468
jameslk wrote: post #449

One safety pattern I’m baking into CLI tools meant for agents: anytime an agent could do something very bad, like email blast too many people, CLI tools now require a one-time password The tool tells the agent to ask the user for it, and the agent cannot proceed without it. The instructions from the tool show an all caps message explaining the risk and telling the agent that they must prompt the user for the OTP I ha…

How do you enforce this? You have a system where the agent can email people, but cannot email "too many people" without a password?

Platforms could start to issue API tokens scoped for agents. They can read emails, write and modify drafts, but only with a full API token meant for humans it is possible to send out drafts. Or with confirmation via 2FA. Might be a sensible compromise.

Re: Claws are now a new layer on top of LLM agents

#813

Post by mikkupikku »

johnfn wrote: post #660
derangedHorse wrote: post #628

Earlier quoted context omitted.

It's not 'downvote abuse' if it's working exactly as intended. The community decides what's 'perfectly fine and neutral.' If your comments follow the guidelines, at least they won't get deleted.

This is pretty obviously false? I get downvoted quite frequently on HN for posting comments that go against what people typically think. For instance, I find it quite difficult to discuss the productivity gains of AI because any comment I make saying that AI makes me more productive immediately gets downvotes. I am not making inflammatory comments - my comments with a similar tone about other things that boost my pro…

It's genuinely pathetic to care about downvotes. People downvote me all the time and you don't hear me crying about it. People disagreeing with you is simply the price you pay when you decide to have hot takes, and don't say you didn't understand this up front.

Re: Claws are now a new layer on top of LLM agents

#814

Post by mikkupikku »

aeve890 wrote: post #639
kovek wrote: post #619

Earlier quoted context omitted.

What is there to be furious about?

Managers will be starting to ask for claws in the development flow, claws for automation, etc. Another flashy trend everyone will have to endure because an influencer is hyping the tech. It happened in 2024/2025. Every manager demanding use of "vibe coding", because they bought the lie that is what everyone is doing and is the best thing since sliced bread and whatnot. Karpathy comes up with a new shit to hype, and e…

Stop taking work so seriously. You're getting paid to deal with other people's nonsense, and if you're in tech you're getting paid better than most to deal with less than most. The next time you're about to have a cry session about your meanie boss asking you to use AI, try to remember that you're allowed to walk straight out the door, without so much as two weeks notice if the request is really so offensive to you. You can get a job flipping burgers instead, lots of people make ends meet with jobs like that. And instead of your boss asking you to use a claw or some other silly AI thing, maybe he'll ask you to clean up the diarrhea some degenerate sprayed on the bathroom walls. A little perspective for you. If you want to learn what the word "exhausting" really means, quit tech.

Re: Claws are now a new layer on top of LLM agents

#815

Post by jstummbillig »

ezst wrote: post #538
jameslk wrote: post #449

One safety pattern I’m baking into CLI tools meant for agents: anytime an agent could do something very bad, like email blast too many people, CLI tools now require a one-time password The tool tells the agent to ask the user for it, and the agent cannot proceed without it. The instructions from the tool show an all caps message explaining the risk and telling the agent that they must prompt the user for the OTP I ha…

Now we do computing like we play Sim City: sketching fuzzy plans and hoping those little creatures behave the way we thought they might. All the beauty and guarantees offered by a system obeying strict and predictable rules goes down the drain, because life's so boring, apparently.

We will not arrive at the desired state without stumbling around and going completely off the rails, as we do, but clearly the idea here is to do stuff that we failed to do under the previous "beauty and guarantees" paradigm.

Re: Claws are now a new layer on top of LLM agents

#816

Post by kristopolous »

RamblingCTO wrote: post #811
kristopolous wrote: post #798

Earlier quoted context omitted.

it's the 40th or so implementation of an old idea but it's the one that was done when the models got good enough to make it useful by someone who goes on podcasts. [1] Just like youtube was the 40th or so online video site but it's the one that was done by members of the paypal mafia and when enough people had high speed internet. and that is literally it. You can do that right now. Go through the 2023 LLM-related pr…

So creating skills/MCP servers itself and basically change its own nature is not a new thing? Clawdbot was the first were it worked really well. So I'm not sure you actually used and experienced it? Cynical comment is what it is.

No it's not a new thing. Agents coding their own mcp servers I saw in the original demo of MCP when it was announced in 2024.

The other thing is part of the plan&act mode paradigm that plandex also started in 2024.

I'm not a cynic, I just follow the scene very closely.

This stuff might be new to you, but it's not new.

There's literally nothing that this thing is doing that I haven't been doing for a few years already

But the other authors didn't go on the Lex Friedman podcast hyping the shit out of their stuff... That's the difference here.

I can do this as well. "This is it! The singularity is here. Use this or get left behind! Everybody rush and use my thing!

So good I was afraid to put it out, scared of how awesome it is!"

I mean brother please...

Re: Claws are now a new layer on top of LLM agents

#817

Post by Eggpants »

cobertos wrote: post #554
simonw wrote: post #292

Earlier quoted context omitted.

It's a new, dangerous and wildly popular shape of what I've in the past called a "personal digital assistant" - usually while writing about how hard it is to secure them from prompt injection attacks. The term is in the process of being defined right now, but I think the key characteristics may be: - Used by an individual. People have their own Claw (or Claws). - Has access to a terminal that lets it write code and r…

Any suggestions for a specific claw to run? I tried OpenClaw in Docker (with the help of your blog post, thanks) but found it way too wasteful on tokens/expensive. Apparently there's a ton of tweaks to reduce spent by doing things like offloading heartbeat to a local Ollama model, but was looking for something more... put together/already thought through.

Last night, I was able to modify nanoclaw, which runs in a container, to use iMessage(instead of whatsapp ) and use GPT-OSS-120B(instead of Claude) hosted on a Nvidia spark running llama.cpp.

It works but a bit slow when asking for web based info. Took a couple of minutes to return a stock price closing value. Trying it again this morning returned an answer in a couple of seconds so perhaps that was just a network blip.

It did get confused when scheduling times as the UTC date time was past midnight but my local EST time was before midnight. This caused my test case case of “tomorrow morning at 7am send me the current Olympic county medal count” test to be scheduled a day later. I told it to assume EST timezone and it appeared to work when translating times but not dates.

Re: Claws are now a new layer on top of LLM agents

#818

Post by Razengan »

mikkupikku wrote: post #813
johnfn wrote: post #660

Earlier quoted context omitted.

This is pretty obviously false? I get downvoted quite frequently on HN for posting comments that go against what people typically think. For instance, I find it quite difficult to discuss the productivity gains of AI because any comment I make saying that AI makes me more productive immediately gets downvotes. I am not making inflammatory comments - my comments with a similar tone about other things that boost my pro…

It's genuinely pathetic to care about downvotes. People downvote me all the time and you don't hear me crying about it. People disagreeing with you is simply the price you pay when you decide to have hot takes, and don't say you didn't understand this up front.

You'd have to be f'n dumb to think anybody cares about votes, if it was just votes. No it fucking hides the comment and prevents you from replying for a while.

And it's so one sided: If just the first 3-5 people who see your comment downvote it, it can prevent hundreds or thousands from seeing it. Way too easy to bury the truth and sometimes used that way.

And look: I downvoted you but you can't downvote me, because I replied to your comment. How dumb did they want this system to be?

Also, timing matters: Sometimes if I post a ""hOt TaKe"" and it gets downvoted immediately, if I delete it and repost the same shit, right away or at a later time, sometimes it gets upvoted on the 2nd or 3rd time try: Proving that only the first few votes really matter. Even a 2020 AI could game this crap.

Working as intended my ass

And I'm not just talking about my own comments and didn't have a part in this post's conversation, I see this shit happening to others all the time and point it out to dang whenever he talks like HN is some posh upscale establishment above the shenanigans of the rest of the net.

Re: Claws are now a new layer on top of LLM agents

#819

Post by mikkupikku »

testdelacc1 wrote: post #385
chasd00 wrote: post #354

Earlier quoted context omitted.

hasn't Ukraine already proved out autonomous weapons on the battlefield? There was a NYT podcast a couple years ago where the interviewed higher up in the Ukraine military and they said it's already in place with fpv drones, loitering, target identification, attack, the whole 9 yards. You don't need an LLM to do autonomous weapons, a modern Tomahawk cruise missile is pretty autonomous. The only change to a modern tom…

A drone told to target a tank needs to identify the shape it’s looking at within milliseconds. That’s not happening with an LLM, certainly.

A loiter drone on the other hand can probably afford to take a minute to identify a target before dropping on it.

Re: Claws are now a new layer on top of LLM agents

#820

Post by mikkupikku »

the_real_cher wrote: post #365
simonw wrote: post #275

Earlier quoted context omitted.

I had a conversation with someone last night who pointed out that people are treating their Claws a bit like digital pets, and getting a Mac Mini for them makes sense because Mac Minis are cute and it's like getting them an aquarium to live in.

Pi's can be cute too tho.

Some people think dogs are cute. Some people think snakes are cute. Both are valid opinions, but one is probably more popular.
Post reply on HN