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

921–930 of 1001 posts

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

#921

Post by unixfg »

kanodiaayush wrote: post #736
unixfg wrote: post #350

Earlier quoted context omitted.

My favorite use so far has been giving it a copy of my Calibre library. After having it write a few scripts and a skill, I can ask it questions about any book I’m reading. This week I had it order a series internally chronological. I could use the search on my Kindle or open Calibre myself, but a Signal message is much faster when it’s already got the SQLite file right there.

This is interesting. Do you mean this is like chat with your book, or these are books you've already finished reading which you have a query over to ask? And does it search raw book text or metadata?

I add books to Calibre in order to load them on my Kindle. Claw gets the Calibre files, including both metadata.db and full-text-search.db, via Syncthing.

I can ask it to perform metadata updates, since it's a two-way sync, or ask questions about the content.

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

#922

Post by SolarNet »

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…

Like usual the answer is it made it easy to use. Think Linux and Windows. You have a customized Linux setup kind of agent. Open claw is the easy install wizard assisted version of that that the masses can easily setup.

It's nothing new, its just the old stuff packaged together and pre-configured.

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

#923

Post by kortilla »

aleph_minus_one wrote: post #873
kortilla wrote: post #668

Earlier quoted context omitted.

How does that make it “obviously false”? The community doesn’t want to hear about how AI isn’t working for people on every AI article. That’s the current balance of votes in the community.

> The community doesn’t want to hear about how AI isn’t working for people on every AI article. The community doesn't want to hear about how AI is the panacea for the problems some people have on every AI article, either.

Don’t read AI articles. The vote balances are a reflection of the current majority opinions. That’s how these voting based social site work, by design.

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

#924

Post by BeetleB »

AlecSchueler wrote: post #427
BeetleB wrote: post #360

Earlier quoted context omitted.

I don't see why you think there is. Put Openclaw on a locked down VM. Don't put anything you're not willing to lose on that VM.

But if we're talking about optionally giving it access to your email, PayPal etc and a "YOLO-outlook on permissions to use your creds" then the VM itself doesn't matter so much as what it can access off site.

So, as so many people have been saying: Don't give it access to (your) email, Paypal, etc.

It's a very general purpose tool. Complaining about it is like complaining that rm will let you delete /

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

#925

Post by BeetleB »

jbxntuehineoh wrote: post #674
billmalarky wrote: post #458

Earlier quoted context omitted.

Bastion hosts. You don't give it your "prod email", you give it a secondary email you created specifically for it. You don't give it your "prod Paypal", you create a secondary paypal (perhaps a paypal account registered using the same email as the secondary email you gave it). You don't give it your "prod bank checking account", you spin up a new checking with Discover.com (or any other online back that takes Now the…

isn't the value proposition "it can read your email and then automatically do things"? if it can't read your email and then can't actually automatically do things... what's the point?

The value proposition is it is an agent with (some) memory. There are lots of use cases that don't involve giving access to your personal stuff. Even a simple "Monitor these companies' career pages and notify me of an opening in my city" is useful.

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

#926

Post by daxfohl »

mejutoco wrote: post #824
daxfohl wrote: post #555

Earlier quoted context omitted.

The rules have changed though. They blocked api access because it helped competitors more than end users. With claws, end users are going to be the ones demanding it. I think it means front-end will be a dead end in a year or two.

My point is that the underlying incentives are exactly the same. I dont think the rules have changed at all. If you are expedia you could always give an api to search forhotels, but why commoditize yourself? Same with agents. Ryanair recently had a court case with some meta travel website because they were selling their flights. Ryanair wants to sell you the insurance and extras, and they can only do so controlling t…

Okay yeah I agree with this. I think there's going to be a whole new subindustry called "Agent eXperience" in the near future that specializes in making workflows like searching, ranking, buying flights straight from airlines easy for agents to do independently on behalf of human preferences, and figuring out how to market add-ons etc to agents as well.

I hadn't thought about the legal aspect, but yeah, eventually some kind of legal moats will probably be dug as well. Just because an agent figures out some workaround to get free flights doesn't mean it has to be honored, I guess.

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

#927

Post by alterom »

heliumtera wrote: post #847
kristopolous wrote: post #816

Earlier quoted context omitted.

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…

You forget to mention the cult like audience of karpathy and pelican guy. Whatever pelican guy says becomes the week Show HN theme.

I hate that I understand what "pelican guy" refers to.

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

#928

Post by akssassin907 »

dwood_dev wrote: post #696
akssassin907 wrote: post #578

Earlier quoted context omitted.

The pattern I found that works ,use a small local model (llama 3b via Ollama, takes only about 2GB) for heartbeat checks — it just needs to answer 'is there anything urgent?' which is a yes/no classification task, not a frontier reasoning task. Reserve the expensive model for actual work. Done right, it can cut token spend by maybe 75% in practice without meaningfully degrading the heartbeat quality. The tricky part…

It seems to me like it would be a rather useful exercise to have the smaller model make the routing decision, and below certain confidence thresholds, it sends it to a larger model anyways. Then have the larger model evaluate that choice and perhaps refine instructions.

That's a cleaner implementation than what I described. Small model as meta-router: classify locally, escalate only when confidence is low. The self-evaluation loop you're suggesting would add a quality layer without much overhead — the large model's judgment of its own routing is itself a useful signal. Haven't shipped that yet but it's on the list.

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

#929

Post by akssassin907 »

what wrote: post #728
akssassin907 wrote: post #578

Earlier quoted context omitted.

The pattern I found that works ,use a small local model (llama 3b via Ollama, takes only about 2GB) for heartbeat checks — it just needs to answer 'is there anything urgent?' which is a yes/no classification task, not a frontier reasoning task. Reserve the expensive model for actual work. Done right, it can cut token spend by maybe 75% in practice without meaningfully degrading the heartbeat quality. The tricky part…

Maybe I’m out of touch but why do you need an LLM to decide if there’s any work to be done? Can’t it just queue or schedule tasks? We already have technology for that that doesn’t require an LLM.

Totally valid for fixed, well-defined tasks — a cron job is cheaper and more reliable there. The LLM earns its keep when the heartbeat involves contextual judgment: not just "is there a task in the queue" but "given everything happening right now, what actually matters?" If the agent needs to reason about priority, relevance, or context before deciding what to surface — that's where the local model pulls its weight. If your agents only do fixed tasks, you're totally right, you don't need it!

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

#930

Post by fennecbutt »

Gotta say I haven't seen anything relevant from "top AI" people in a while now.

I think as soon as you get involved in the MBA C level world of finance and shareholders then your life as a scientist is over.

It's now all just self marketing. I suppose we'd all do the same...

Post reply on HN