Live data from Hacker News

Claws are now a new layer on top of LLM agents

twitter.com

611–620 of 1001 posts

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

#611
post #599

Earlier quoted context omitted.

what's a shell script? sounds like an implementation detail that I don't care about, I just want something to do a thing for me.

I let out a big sigh reading this and would like to move to a different planet now.

I'm channeling other people. But that's what most people want, just the problem solved for them. Not to write programs.

I love doing mechanical things, I also just want my truck to run.

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

#612
post #419

All: quite a few comments in this thread (and another one we merged hither - https://news.ycombinator.com/item?id=47099160 ) have contained personal attacks. Hopefully most of them are [flagged] and/or [dead] now. On HN, please don't cross into personal attack no matter how strongly you feel about someone or disagree with them. It's destructive of what the site is for, and we moderate and/or ban accounts that do it.…

[flagged]

Being rude isn't helpful. It's not their fault, it's the unavoidable reality of treating complex social signalling as one-dimensional. At minimum Hacker News would need to separate approval/disapproval signals from assessments of whether a comment is constructive. That’s not a simple change given the obvious abuse vectors. It would require reliably distinguishing good-faith participants from bad actors. It can be done, but it's not easy.

The main reason sites avoid this approach is institutional rather than technical. Adding algorithmic mediation invites accusations of algorithmic bias whenever results are unpopular.[0] Simple manual interventions are often sufficient to nudge community behaviour so that majority outcomes broadly align with the moderators’ priors, without the visibility or accountability costs of a more complex system.

[0] Case in point being X. People routinely accuse the new management of "juicing" the algorithm to favour their politics, when outcomes are adequately explained by the exodus of contributors on the other side. Isolating innate community bias from algorithms is a philosophically impossible problem.

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

#613
post #525

Earlier quoted context omitted.

Andrej is an extremely effective communicator and educator. But I don't agree that he is one of the most significant AI pioneers in history. His research contributions are significant but not exceptional compared to other folks around him at the time. He got famous for free online courses, not his research. His work at Tesla was not exactly a rousing success. Today I see him as a major influence in how people, especi…

You can debate the meaning of the word pioneer but think of it this way: OpenAI created this new AI boom, and Andrej is a co-founder of the company that did that.

Would you say that Musk is one of the most significant AI pioneers in history? I don't personally believe that founding the organization is more meaningful than doing the actual work.

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

#614

I still dont understand the hype for any of this claw stuff

It’s as if ChatGPT is an autonomous agent that can do anything and keeps running constantly. Most AI tools require supervision, this is the opposite. To many people, the idea of having an AI always active in the background doing whatever they want them to do is interesting.

> It’s as if ChatGPT is an autonomous agent that can do anything and keeps running constantly.

Really stretching the definition of "anything."

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

#615
post #481

Earlier quoted context omitted.

This sounds like it would be better suited for a shell script.

what's a shell script? sounds like an implementation detail that I don't care about, I just want something to do a thing for me.

Enjoy losing your money, getting your personal information leaked, and possibly getting arrested when and if it does something illegal on your command.

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

#617

Does one really need to _buy_ a completely new desktop hardware (ie. mac mini) to _run_ a simple request/response program? Excluding the fact that you can run LLMs via ollama or similar directly on the device, but that will not have a very good token/s speed as far as I can guess...

What other device would you suggest as a home server that a non tech person can set up themselves and has enough power to run several Chrome tabs? Access to iMessage is a plus. Small beeline Windows devices could also work but it’s Windows 11, slow as molasses.

Raspberry Pi using Pi OS

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

#618

I'm confused and frustrated by this naming of "claws" * I think my biggest frustration is that I don't know how security standards just gets blatantly ignored for the sake of ai progress. It feels really weird that folks with huge influence and reputation in software engineering just promotes this * The confusion comes in because for some reason we decide to drop our standards at a whim. Lines of code as the measurem…

maybe they are enthusiastic about the evolution.

thousands of copies of shitty code, only the best will survive

I know it's hard to be enthusiastic about bad code, but worked well enough for the evolution of life on earth

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

#619
post #419

All: quite a few comments in this thread (and another one we merged hither - https://news.ycombinator.com/item?id=47099160 ) have contained personal attacks. Hopefully most of them are [flagged] and/or [dead] now. On HN, please don't cross into personal attack no matter how strongly you feel about someone or disagree with them. It's destructive of what the site is for, and we moderate and/or ban accounts that do it.…

[flagged]

What is there to be furious about?

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

#620

Earlier quoted context omitted.

I've been hoping one of them will be called Clod

I appreciate the sentiment, but think a homophone would be too confusing.

Confusion is only temporary until we're replaced by agentic giga nerd superintelligence /s
Post reply on HN