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

Claude Skills

anthropic.com

Post reply on HN
Print view View original

121–130 of 443 posts

Re: Claude Skills

#121

Post by dingnuts »

mediaman wrote: post #111
mbesto wrote: post #90

Earlier quoted context omitted.

> Contrast with the way a human learns skills - as we gain experience with a skill, we get better at understanding when it's the right tool for the job. Which is precisely why Richard Sutton doesn't think LLMs will evolve to AGI[0]. LLMs are based on mimicry, not experience, so it's more likely (according to Sutton) that AGI will be based on some form of RL (reinforcement learning) and not neural networks (LLMs). Mor…

It's a false dichotomy. LLMs are already being trained with RL to have goal directedness. He is right that non-RL'd LLMs are just mimicry, but the field already moved beyond that.

Explain something to me that I've long wondered: how does Reinforcement Learning work if you cannot measure your distance from the goal? In other words, how can RL be used for literally anything qualitative?

Re: Claude Skills

#123

Post by anomaloustho »

mediaman wrote: post #111
mbesto wrote: post #90

Earlier quoted context omitted.

> Contrast with the way a human learns skills - as we gain experience with a skill, we get better at understanding when it's the right tool for the job. Which is precisely why Richard Sutton doesn't think LLMs will evolve to AGI[0]. LLMs are based on mimicry, not experience, so it's more likely (according to Sutton) that AGI will be based on some form of RL (reinforcement learning) and not neural networks (LLMs). Mor…

It's a false dichotomy. LLMs are already being trained with RL to have goal directedness. He is right that non-RL'd LLMs are just mimicry, but the field already moved beyond that.

I wrote elsewhere but I’m more interpreting this distinction as “RL in real-time” vs “RL beforehand”.

Re: Claude Skills

#124

Post by dingnuts »

ryancnelson wrote: post #72
zobzu wrote: post #48

Earlier quoted context omitted.

IMO this is a context window issue. Humans are pretty good are memorizing super broad context without great accuracy. Sometimes our "recall" function doesn't even work right ("How do you say 'blah' in German again?"), so the more you specialize (say, 10k hours / mastery), the better you are at recalling a specific set of "skills", but perhaps not other skills. On the other hand, LLMs have a programatic context with c…

I commented here already about deli-gator ( https://github.com/ryancnelson/deli-gator ) , but your summary nailed what I didn’t mention here before: Context. I’d been re-teaching Claude to craft Rest-api calls with curl every morning for months before i realized that skills would let me delegate that to cheaper models, re-using cached-token-queries, and save my context window for my actual problem-space CONTEXT.

>I’d been re-teaching Claude to craft Rest-api calls with curl every morning for months

what the fuck, there is absolutely no way this was cheaper or more productive than just learning to use curl and writing curl calls yourself. Curl isn't even hard! And if you learn to use it, you get WAY better at working with HTTP!

You're kneecapping yourself to expend more effort than it would take to just write the calls, helping to train a bot to do the job you should be doing

Re: Claude Skills

#126

Post by throwup238 »

lukev wrote: post #110
iyn wrote: post #105

Does anyone know how skills relate to subagents? Seems that subagents have more capabilities (e.g. can access the internet) but seems that there's a lot of overlap. I've asked Claude and this it answered this: Skills = Instructions + resources for the current Claude instance (shared context) Subagents = Separate AI instances with isolated contexts that can work in parallel (different context windows) Skills make Clau…

How this reads to me is that a skill is "just" a bundle of prompts, scripts, and files that can be read into context as a unit. Having a sub-agent "execute" a skill makes a lot of sense from a context management, perspective, but I think the way to think about it is that a sub-agent is an "execution-level" construct, whereas a skill is a "data-level" construct.

Skills can also contain scripts that can be executed in a VM. The Anthropic engineering blog mentions that you can specify in the markdown instructions whether the script should be executed or read into context. One of their examples is a script to extract properties from a PDF file.

Re: Claude Skills

#128

Post by jmtulloss »

dingnuts wrote: post #124
ryancnelson wrote: post #72

Earlier quoted context omitted.

I commented here already about deli-gator ( https://github.com/ryancnelson/deli-gator ) , but your summary nailed what I didn’t mention here before: Context. I’d been re-teaching Claude to craft Rest-api calls with curl every morning for months before i realized that skills would let me delegate that to cheaper models, re-using cached-token-queries, and save my context window for my actual problem-space CONTEXT.

>I’d been re-teaching Claude to craft Rest-api calls with curl every morning for months what the fuck, there is absolutely no way this was cheaper or more productive than just learning to use curl and writing curl calls yourself. Curl isn't even hard! And if you learn to use it, you get WAY better at working with HTTP! You're kneecapping yourself to expend more effort than it would take to just write the calls, helpi…

My interpretation of the parent comment was that they were loading specific curl calls into context so that Claude could properly exercise the endpoints after making changes.

Re: Claude Skills

#129

Post by josefresco »

prng2021 wrote: post #7
phildougherty wrote: post #4

getting hard to keep up with skills, plugins, marketplaces, connectors, add-ons, yada yada

Yep. Now I need an AI to help me use AI

Joking aside, I ask Claude how to uses Claude... all the time! Sometimes I ask ChatGTP about Claude. It actually doesn't work well because they don't imbue these AI tools with any special knowledge about how they work, they seem to rely on public documentation which usually lags behind the breakneck pace of these feature-releases.

Re: Claude Skills

#130

Post by baxtr »

mediaman wrote: post #111
mbesto wrote: post #90

Earlier quoted context omitted.

> Contrast with the way a human learns skills - as we gain experience with a skill, we get better at understanding when it's the right tool for the job. Which is precisely why Richard Sutton doesn't think LLMs will evolve to AGI[0]. LLMs are based on mimicry, not experience, so it's more likely (according to Sutton) that AGI will be based on some form of RL (reinforcement learning) and not neural networks (LLMs). Mor…

It's a false dichotomy. LLMs are already being trained with RL to have goal directedness. He is right that non-RL'd LLMs are just mimicry, but the field already moved beyond that.

So it’s on-the-fly adaptive mimicry?
Post reply on HN