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

111–120 of 443 posts

Re: Claude Skills

#111

Post by mediaman »

mbesto wrote: post #90
Imnimo wrote: post #37

I feel like a danger with this sort of thing is that the capability of the system to use the right skill is limited by the little blurb you give about what the skill is for. 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. But Claude is always starting from ground zero and skimming your descriptions.

> 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.

Re: Claude Skills

#112

Post by lukev »

pixelpoet wrote: post #56

Aside: I really love Anthropic's design language, so beautiful and functional.

I agree 100%, except for the logo, which persistently looks like something they... probably did not intend.

Re: Claude Skills

#113

Post by vonneumannstan »

mbesto wrote: post #90
Imnimo wrote: post #37

I feel like a danger with this sort of thing is that the capability of the system to use the right skill is limited by the little blurb you give about what the skill is for. 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. But Claude is always starting from ground zero and skimming your descriptions.

> 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…

This is an uninformed take. Much of the improvement in performance of LLM based models has been through RLHF and other RL techniques.

Re: Claude Skills

#115

Post by antiloper »

buildbot wrote: post #99
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/

"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.

Re: Claude Skills

#116

Post by input_sh »

marcusestes wrote: post #43
phildougherty wrote: post #4

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

Agreed, but I think it's actually simple. Plugins include: * Commands * MCPs * Subagents * Now, Skills Marketplaces aggregate plugins.

It's so simple you didn't even name all of them properly.

Re: Claude Skills

#117

Post by skurilyak »

mbesto wrote: post #90
Imnimo wrote: post #37

I feel like a danger with this sort of thing is that the capability of the system to use the right skill is limited by the little blurb you give about what the skill is for. 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. But Claude is always starting from ground zero and skimming your descriptions.

> 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…

Besides a "reference manual", Claude Skills is analogous to a "toolkit with an instruction manual" in that it includes both instructions (manuals) and executable functions (tools/code)

Re: Claude Skills

#118

Post by leptons »

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 can't wait to try to convince an LLM/RL/whatever-it-is that what it "thinks" is right is actually wrong.
Post reply on HN