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

181–190 of 443 posts

Re: Claude Skills

#181

Post by munchler »

anomaloustho wrote: post #123
mediaman wrote: post #111

Earlier quoted context omitted.

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”.

I agree with this description, but I'm not sure we really want our AI agents evolving in real time as they gain experience. Having a static model that is thoroughly tested before deployment seems much safer.

Re: Claude Skills

#183

Post by Der_Einzige »

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:…

Tool use is only good with structured/constrained generation

Re: Claude Skills

#184

Post by libraryofbabel »

Der_Einzige wrote: post #183
libraryofbabel wrote: post #180

Earlier quoted context omitted.

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:…

Tool use is only good with structured/constrained generation

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

Re: Claude Skills

#185

Post by ChadMoran »

fragmede wrote: post #146
ChadMoran wrote: post #108

Earlier quoted context omitted.

This is the crux of knowledge/tool enrichment in LLMs. The idea that we can have knowledge bases and LLMs will know WHEN to use them is a bit of a pipe dream right now.

Can you be more specific? The simple case seems to be solved, eg if I have an mcp for foo enabled and then ask about a list of foo, Claude will go and call the list function on foo.

It doesn't reliably do it. You need to inject context into the prompt to instruct the LLM to use tools/kb/etc. It isn't deterministic of when/if it will follow-through.

Re: Claude Skills

#186

Post by taejavu »

josefresco wrote: post #143

I just used tested the canvas-design skill and the results were pretty awful. This is the skill description: Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. What it created was a…

If you want to generate images, use Midjourney or whatever. It’s almost like you’ve deliberately missed the point of the feature.

Re: Claude Skills

#188

Post by __loam »

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.

Langchain was the original sin of thin framework bullshit

Re: Claude Skills

#189

Post by dlivingston »

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:…

> Call it what you want, you can write it in 100 lines of Python. I encourage every programmer I talk to who is remotely curious about LLMs to try that. It is a lightbulb moment.

Definitely want to try this out. Any resources / etc. on getting started?

Re: Claude Skills

#190

Post by mbesto »

munchler wrote: post #181
anomaloustho wrote: post #123

Earlier quoted context omitted.

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

I agree with this description, but I'm not sure we really want our AI agents evolving in real time as they gain experience. Having a static model that is thoroughly tested before deployment seems much safer.

> Having a static model that is thoroughly tested before deployment seems much safer.

While that might true, it fundamentally means it's not going to ever replicate human or provide super intelligence.

Post reply on HN