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

371–380 of 1001 posts

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

#371

Post by nradov »

deepsquirrelnet wrote: post #277
claytonaalves wrote: post #219

I'm impressed with how we moved from "AI is dangerous", "Skynet", "don't give AI internet access or we are doomed", "don't let AI escape" to "Hey AI, here is internet, do whatever you want".

The DoDs recent beef with Anthropic over their right to restrict how Claude can be used is revealing. > Though Anthropic has maintained that it does not and will not allow its AI systems to be directly used in lethal autonomous weapons or for domestic surveillance Autonomous AI weapons is one of the things the DoD appears to be pursuing. So bring back the Skynet people, because that’s where we apparently are. 1. http…

The DoD was pursuing autonomous AI weapons decades ago, and succeeded as of 1979 with the Mk 60 Captor Mine.

https://www.vp4association.com/aircraft-information-2/32-2/m...

The worries over Skynet and other sci-fi apocalypse scenarios are so silly.

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

#372

Post by mkw5053 »

zozbot234 wrote: post #295
nsonha wrote: post #290

I find it dubious that a technical person claims to "just bought a new Mac mini to properly tinker with claws over the weekend". Like can they not just play with it on an old laptop lying around? A virtual machine? Or why did they not buy a Pi instead? Openclaw works with linux so not sure how this whole Mac mini cliche even started, obviously an overkill for something that only relays api calls.

Using a Mac Mini allows for better integration with existing Apple services. For many users, that just makes sense.

Exactly, especially iMessage. It's fair to think that's not worth it, but for those who choose to use it, it is.

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

#373

Post by GuB-42 »

claytonaalves wrote: post #219

I'm impressed with how we moved from "AI is dangerous", "Skynet", "don't give AI internet access or we are doomed", "don't let AI escape" to "Hey AI, here is internet, do whatever you want".

We didn't "moved from", both points of view exist. Depending on the news, attention may shifts from one to another.

Anyways, I don't expect Skynet to happen. AI-augmented stupidity may be a problem though.

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

#374

Post by lmf4lol »

lifty wrote: post #352
lmf4lol wrote: post #299

Earlier quoted context omitted.

a lot of really fun stuff. From fun little scripts to more complex business/life/hibby admin stuff that annoyed me a lot (eg organizing my research). for instance i can just drop it a YT link in Telegram, and it then will automatically download the transcripts, scan them, and match them to my research notes. If it detects overlap it will suggest a link in the knowledge base. Works super nice for me because i am a cha…

What model do you use it with? And through which API, openrouter? Wondering how you manage cost because it can get quite expensive

I am dumb. I use Anthropic Api and Opus for some, Sonnet for other tasks. Accumulated quite some costs.

But i book it as a business expense , so its less painful as if it would be for private.

But yeah, could optimize for cost more

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

#375

Post by ttul »

logicprog wrote: post #362
ttul wrote: post #351

Earlier quoted context omitted.

The ZeroClaw team is focusing their efforts on correctness and security by design. Observability is not yet there but the project is moving very rapidly. Their approach, I believe, is right for the long term.

There's a reason I chose ZC to try first! Out of all of them, it does seem to be the best. I'm just not sure that claws, as an overall thing, are useful yet. at least with any model less capable than Opus 4.6 — and if you're using opus, then whew, that's expensive and wasteful.

Regarding models, I’ve found that going with OpenRouter’s `auto` model works well enough, choosing the powerful models when they seem to be needed, and falling back on cheaper ones for other queries. But, it’s still expensive…

Depending on what you want your claw to do, Gemini Flash can get you pretty far for pennies.

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

#376

Post by nradov »

jryan49 wrote: post #247
claytonaalves wrote: post #219

I'm impressed with how we moved from "AI is dangerous", "Skynet", "don't give AI internet access or we are doomed", "don't let AI escape" to "Hey AI, here is internet, do whatever you want".

I mean we know at this point it's not super intelligent AGI yet, so I guess we don't care.

There is no scientific basis to expect that the current approach to AI involving LLMs could ever scale up to super intelligent AGI. Another major breakthrough will be needed first, possibly an entirely new hardware architecture. No one can predict when that will come or what it will look like.

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

#377

Post by bcrosby95 »

wolttam wrote: post #343
samiv wrote: post #314

Earlier quoted context omitted.

It's ok we'll just send a robot back in time to help destroy the chip that starts it.

Judging by what's going on around me, it failed :(

We're just stuck in the non-diverged timeline that's fucked.

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

#378

Post by tim333 »

chasd00 wrote: post #358
zer00eyz wrote: post #303

Earlier quoted context omitted.

> Autonomous AI weapons In theory, you can do this today, in your garage. Buy a quad as a kit. (cheap) Figure out how to arm it (the trivial part). Grab yolo, tuned for people detection. Grab any of the off the shelf facial recognition libraries. You can mostly run this on phone hardware, and if you're stripping out the radios then possibly for days. The shim you have to write: software to fly the drone into the pers…

> software to fly the drone into the person... and thats probably around somewhere out there as well. ardupilot + waypoint nav would do it for fixed locations. The camera identifies a target, gets the gps cooridnates and sets a waypoint. I would be shocked if there wasn't extensions available (maybe not officially) for flying to a "moving location". I'm in the high power rocketry hobby and the knowledge to add contro…

The Ukrainian drones that took out Russia's long range bombers used ArduPilot and AI. (https://en.wikipedia.org/wiki/Operation_Spiderweb)

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

#379

Post by phba »

chasd00 wrote: post #358
zer00eyz wrote: post #303

Earlier quoted context omitted.

> Autonomous AI weapons In theory, you can do this today, in your garage. Buy a quad as a kit. (cheap) Figure out how to arm it (the trivial part). Grab yolo, tuned for people detection. Grab any of the off the shelf facial recognition libraries. You can mostly run this on phone hardware, and if you're stripping out the radios then possibly for days. The shim you have to write: software to fly the drone into the pers…

> software to fly the drone into the person... and thats probably around somewhere out there as well. ardupilot + waypoint nav would do it for fixed locations. The camera identifies a target, gets the gps cooridnates and sets a waypoint. I would be shocked if there wasn't extensions available (maybe not officially) for flying to a "moving location". I'm in the high power rocketry hobby and the knowledge to add contro…

> a hobby that already raises eyebrows

Sounds very interesting, but may I ask how this actually works as a hobby? Is it purely theoretical like analyzing and modeling, or do you build real rockets?

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

#380

Post by davedx »

I run a Discord where we've had a custom coded bot I created since before LLM's became useful. When they did, I integrated the bot into LLMs so you could ask it questions in free text form. I've gradually added AI-type features to this integration over time, like web search grounding once that was straightforward to do.

The other day I finally found some time to give OpenClaw a go, and it went something like this:

- Installed it on my VPS (I don't have a Mac mini lying around, or the inclination to just go out and buy one just for this)

- Worked through a painful path of getting it a browser working (VPS = no graphics subsystem...)

- Decided as my first experiment, to tell it to look at trading prediction markets (Polymarket)

- Discovered that I had to do most of the onboarding for this, for numerous reasons like KYC, payments, other stuff OpenClaw can't do for you...

- Discovered that it wasn't very good at setting up its own "scheduled jobs". It was absolutely insistent that it would "Check the markets we're tracking every morning", until after multiple back and forths we discovered... it wouldn't, and I had to explicitly force it to add something to its heartbeat

- Discovered that one of the bets I wanted to track (fed rates change) it wasn't able to monitor because CME's website is very bot-hostile and blocked it after a few requests

- Told me I should use a VPN to get around the block, or sign up to a market data API for it

- I jumped through the various hoops to get a NordVPN account and run it on the VPS (hilariously, once I connected it blew up my SSH session and I had to recovery console my way back in...)

- We discovered that oh, NordVPN's IP's don't get around the CME website block

- Gave up on that bet, chose a different one...

- I then got a very blunt WhatsApp message "Usage limit exceeded". There was nothing in the default 'clawbot logs' as to why. After digging around in other locations I found a more detailed log, yeah, it's OpenAI. Logged into the OpenAI platform - it's churned through $20 of tokens in about 24h.

At this point I took a step back and weighted the pros and cons of the whole thing, and decided to shut it down. Back to human-in-the-loop coding agent projects for me.

I just do not believe the influencers who are posting their Clawbots are "running their entire company". There are so many bot-blockers everywhere it's like that scene with the rakes in the Simpsons...

All these *claw variants won't solve any of this. Sure you might use a bit less CPU, but the open internet is actually pretty bot-hostile, and you constantly need humans to navigate it.

What I have done from what I've learned though, is upgrade my trusty Discord bot so it now has a SOUL.md and MEMORIES.md. Maybe at some point I'll also give it a heartbeat, but I'm not sure...

Post reply on HN