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

201–210 of 443 posts

Re: Claude Skills

#201

Post by mbesto »

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.

> LLMs are already being trained with RL to have goal directedness.

That might be true, but we're talking about the fundamentals of the concept. His argument is that you're never going to reach AGI/super intelligence on an evolution of the current concepts (mimicry) even through fine tuning and adaptions - it'll like be different (and likely based on some RL technique). At least we have NO history to suggest this will be case (hence his argument for "the bitter lesson").

Re: Claude Skills

#202

Post by tgtweak »

antiloper wrote: post #115
buildbot wrote: post #99

Earlier quoted context omitted.

"So I fired up a fresh Claude instance (fun fact: Code Interpreter also works in the Claude iOS app now, which it didn't when they first launched) and prompted: Create a zip file of everything in your /mnt/skills folder" It's a fun, terrifying world that this kind of "hack" to exfiltrate data is possible! I hope it does not have full filesystem/bin access, lol. Can it SSH?...

What's the hack? Instead of typing `zip -r mnt.zip /mnt` into bash, you type `Create a zip file of /mnt` in claude code. It's the same thing running as the same user.

Skills run remotely in the llm environment, not locally on your system running claude - worth noting.

Re: Claude Skills

#203

Post by cesarvarela »

fridder wrote: post #38

All of these random features is just pushing me further towards model agnostic tools like goose

I wonder how much this affects the model's performance. I imagine Anthropic trains its models to use a generic set of tools, but they can also lean on their specific tool definitions to save the agent from having to guess which tool for what.

Re: Claude Skills

#204

Post by mbesto »

kmacdough wrote: post #154
dingnuts wrote: post #121

Earlier quoted context omitted.

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?

This is one of known hardest parts of RL. The short answer is human feedback. But this is easier said than done. Current models require vastly more learning events than humans, making direct supervision infeasable. One strategy is to train models on human supervisors, so they can bear the bulk of the supervision. This is tricky, but has proven more effective than direct supervision. But, in my experience, AIs don't s…

This 100%.

While we might agreed that language is foundational to what it is to be human, it's myopic to think its the only thing. LLMs are based on training sets of language (period).

Re: Claude Skills

#205

Post by mritchie712 »

mousetree wrote: post #25

I'm perplexed why they would use such a silly example in their demo video (rotating an image of a dog upside down and cropping). Surely they can find more compelling examples of where these skills could be used?

this is the best example I found

https://github.com/anthropics/skills/blob/main/document-skil...

I was dealing with 2 issues this morning getting Claude to produce a .xlsx that are covered in the doc above

Re: Claude Skills

#206

Post by AStrangeMorrow »

libraryofbabel wrote: post #184
Der_Einzige wrote: post #183

Earlier quoted context omitted.

Tool use is only good with structured/constrained generation

You'll need to expand on what you mean, I'm afraid.

I think, from my experience, what they mean is tool use is as good as your model capability to stick to a given answer template/grammar. For example if it does tool calling using a JSON format it needs to stick to that format, not hallucinate extra fields and use the existing fields properly. This has worked for a few years and LLMs are getting better and better but the more tools you have, the more parameters your functions to call can have etc the higher the risk of errors. You also have systems that constrain the whole inference itself, for example with the outlines package, by changing the way tokens are sampled (this way you can force a model to stick to a template/grammar, but that can also degrade results in some other ways)

Re: Claude Skills

#207

Post by skylurk »

simonw wrote: post #89

I accidentally leaked the existence of these last Friday, glad they officially exist now! https://simonwillison.net/2025/Oct/10/claude-skills/

Woah, Jesse's blog has really come alive lately. Thanks for highlighting this post.

Re: Claude Skills

#208

Post by jjfoooo4 »

JyB wrote: post #151
mercurialsolo wrote: post #133

Sub agents, mcp, skills - wonder how are they supposed to interact with each other? Feels like fair bit of overlap here. It's ok to proceed in a direction where you are upgrading the spec and enabling claude wth additional capabilities. But one can pretty much use any of these approaches and end up with the same capability for an agent. Right now feels like a ux upgrade from mcp where you need a json but instead can…

Claude Skills just seem to be the same as MCP prompts: https://modelcontextprotocol.io/specification/2025-06-18/ser... I don't really see why they had to create a different concept. Maybe makes sense "marketing-wise" for their chat UI, but in Claude Code? Especially when CLAUDE.md is a thing?

I see this as a lower overhead replacement for MCP. Rather than managing a bunch of MCP's, use the directory structure to your advantage, leverage the OS's capability to execute

Re: Claude Skills

#209

Post by ibejoeb »

libraryofbabel wrote: post #180
fny wrote: post #142

I fear the conceptual churn we're going to endure in the coming years will rival frontend dev. Across ChatGPT and Claude we now have tools, functions, skills, agents, subagents, commands, and apps, and there's a metastasizing complex of vibe frameworks feeding on this mess.

You forgot mcp-everything! Yes, it's a mess, and there will be a lot of churn, you're not wrong, but there are foundational concepts underneath it all that you can learn and then it's easy to fit insert-new-feature into your mental model. (Or you can just ignore the new features, and roll your own tools. Some people here do that with a lot of success.) The foundational mental model to get the hang of is really just:…

Pretty true, and definitely a good exercise. But if we're going to actual use these things in practice, you need more. Things like prompt caching, capabilities/constraints, etc. It's pretty dangerous to let an agent go hog wild in an unprotected environment.

Re: Claude Skills

#210

Post by ibejoeb »

anomaloustho wrote: post #109
buildbot wrote: post #93

Earlier quoted context omitted.

The industry has been doing RL on many kinds of neural networks, including LLMs, for quite some time. Is this person saying we RL on some kind of non neural network design? Why is that more likely to bring AGI than an LLM?. > More specifically, LLMs don't have goals and consequences of actions, which is the foundation for intelligence. Citation?

Looks like they added the link. But I think it’s doing RL in realtime vs pre-trained as an LLM is. And I associate that part to AGI being able to do cutting edge research and explore new ideas like humans can. Where, when that seems to “happen” with LLMs it’s been more debatable. (e.g. there was an existing paper that the LLM was able to tap into) I guess another example would be to get an AGI doing RL in realtime to…

I don't think any of the commercial models are doing RL at the consumer. The R is just accepting or rejecting the action, right?
Post reply on HN