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

151–160 of 443 posts

Re: Claude Skills

#151

Post by JyB »

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?

Re: Claude Skills

#152

Post by kbar13 »

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.

i’m letting the smarter folks figure all this out and just picking the tools i like every now and then. i like just using claude code with vscode and still doing some things manually

Re: Claude Skills

#153

Post by esafak »

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.

On the other hand, this complexity represents a new niche that, for a while at least, will present job and business opportunities.

Re: Claude Skills

#154

Post by kmacdough »

dingnuts wrote: post #121
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.

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 specifically struggle with the "qualitative" side of things per-se. In fact, they're great at things like word choice, color theory, etc. Rather, they struggle to understand continuity, consequence and to combine disparate sources of input. They also suck at differentiating fact from fabrication. To speculate wildly, it feels like it's missing the the RL of living in the "real world". In order to eat, sleep and breath, you must operate within the bounds of physics and society and live forever with the consequences of an ever-growing history of choices.

Re: Claude Skills

#155

Post by OtherShrezzing »

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.

In the interview transcript, he seems aware that the field is doing RL, and he makes a compelling argument that bootstrapping isn’t as scalable as a purely RL trained AI would be.

Re: Claude Skills

#156

Post by Trias11 »

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.

Right.

I focus on building projects delivering some specific business value and pick the tools that gets me there.

There is zero value in spending cycles by engaging in new tools hype.

Re: Claude Skills

#158

Post by dalmo3 »

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.

For Cursor: cursorrules, mdc rules, user rules, team rules.

Re: Claude Skills

#159

Post by catgary »

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.

These companies are also biased towards solutions that will more-or-less trap you in a heavily agent-based workflow.

I’m surprised/disappointed that I haven’t seen any papers out of the programming languages community about how to integrate agentic coding with compilers/type system features/etc. They really need to step up, otherwise there’s going to be a lot of unnecessary CO2 produced by tools like this.

Re: Claude Skills

#160

Post by benterix »

mathattack wrote: post #150
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.

There's so much white space - this is the cost of a brand new technology. Similar issues with figuring out what cloud tools to use, or what python libraries are most relevant. This is also why not everyone is an early adopter. There are mental costs involved in staying on top of everything.

> This is also why not everyone is an early adopter.

Usually, there are relatively few adopters of a new technology.

But with LLMs, it's quite the opposite: there was a huge number of early adopters. Some got extremely excited and run hundreds of agents all the time, some got burned and went back to the good old ways of doing things, whereas the majority is just using LLMs from time to time for various tasks, bigger of smaller.

Post reply on HN