Earlier quoted context omitted.
abstractions all the way down: abstraction abstraction abstraction abstraction ...
... absturtles
this is pure absturtity! ("absturtlety"?)
Claude Skills
371–380 of 443 posts
Re: Claude Skills
#372Earlier quoted context omitted.
I always find it hilarious and painfully ironic that Anthropic can't even keep Claude Code's docs up to date. I don't know how much to read into it, but it is a modern marvel of process failure. The team is obviously doing a lot of cool things very rapidly, so I don't want to be too negative, but ... please just ask Claude to review your own docs before you merge a change.
Not saying you’re wrong, but can you cite a couple of examples?
Looking through the issues tagged "documentation" provides many examples (https://github.com/anthropics/claude-code/issues?q=label%3Ad...). It's so common they have an issue template for "Missing documentation (feature not documented)".
Here are a few recent open ones: - "Documentation missing for new 'Explore' subagent" - https://github.com/anthropics/claude-code/issues/9595 - "Missing documentation for modifying tool inputs in PreToolUse hooks" - https://github.com/anthropics/claude-code/issues/9185 - "Missing Documentation for Various Claude Code Features (CLI Flags, Slash Commands, & Tools)" - https://github.com/anthropics/claude-code/issues/8584
Re: Claude Skills
#373I 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
yeah, avoiding all the serialization and deserialization, as I'm already working in Markdown and open text for almost all my stuff. The Claude Skill only seems to make sense for people who don't have their data in multiple different proprietary formats, then it might sense to packaging them into another one. But this can get messy pretty quick!
Re: Claude Skills
#374I've been using Claude at work for the past two months, and the other day I realized that during that time, I haven't had my previously weekly aha moment while in the shower or on a walk where the solution to a problem suddenly came to me. Claude has robbed me of that joy, which is why I got into software engineering. Now I review its slop or the slop that other engineers make with it. I think I'll take a walk today.
Re: Claude Skills
#375Earlier quoted context omitted.
>and if you’re training an agent for this specific task anyway, you’re effectively locking yourself to that specific LLM in perpetuity rather than a replaceable or promotable worker. That's ONE of the long games that are currently played, and is arguably their fallback strategy: The equivalent of vendor lock-in but for LLM providers.
From my IT POV, that’s what this is all about. It’s why none of these major players produce locally-executable LLMs (Mistral, Llama, and DeepSeek being notable exceptions), it’s why their interfaces are predominantly chat-based (to reduce personal skills growth and increase dependency on the chatbot), it’s why they keep churning out new services like Skills and Agents and “Research”, etc. If any of these outfits trul…
"It’s why none of these major players produce locally-executable LLMs (Mistral, Llama, and DeepSeek being notable exceptions)"
OpenAI have gpt-oss-20b and 120b. Google have the Gemma 3 models. At this point the only significant AI lab that doesn't provide a locally executable model are Anthropic!
Re: Claude Skills
#376Earlier quoted context omitted.
then submit it, you don't need to post here about it
i found it useful and coinstructive to post it here also. no reason not to.
In my opinion because this is a discussion about this announcement, and it kinda feels like with not one but _two_ top-level posts, Simon is just kinda trying to hijack this conversation and turn it into a conversation about his posts. I'm not saying Simon is spamming, because there's definitely some relevance here. But I am saying Simon is attention-seeking in an unbecoming manner. Simon's posts make the homepage regularly anyway, he doesn't need to post them in other threads.
Re: Claude Skills
#377With these patterns emerging, does anyone know how local LLMs are faring? It seems to me that by combining MCP and "skills", we are adopting LLMs to be more useful tools; with MCP we restrict input and output when dealing with APIs so that the LLM can do what it is good at; translate between languages - in this case from English to various json subsets - and back. And with skills we're serializing and formalizing pro…
This is definitely a problem. Skills require a very strong model - one with a longer context (32,000 tokens minimum at a guess) that can reliably drive Unix CLI tools over a multiple step conversation.
I haven't yet run a local model that feels strong enough at these things for skills to make sense. Really I think the unlock for skills was o3/Claude 4/GPT-5 - prior to those the models weren't capable enough for something like skills to work well.
That said, the rate of improvement of local models has been impressive over the past 18 months. It's possible we have a 70B local model that's capable enough to run skills now and I've not yet used it with the right harness.
Re: Claude Skills
#378This is interesting, and I think there are use cases where this feature may make sense. But this is not the feature they should or could have built, at least for Claude Code. CC already had a feature very similar to this -- subagents (or agents-as-tools). Like Skills, Subagents have a metadata description that allows the model to choose to use them in the right moment. Like Skills, Subagents can have their own instru…
I think skills and subagents are entirely complementary to each other.
A subagent can use a skill.
A skill can encourage the agent to run a subagent.
Re: Claude Skills
#379I've been using Claude at work for the past two months, and the other day I realized that during that time, I haven't had my previously weekly aha moment while in the shower or on a walk where the solution to a problem suddenly came to me. Claude has robbed me of that joy, which is why I got into software engineering. Now I review its slop or the slop that other engineers make with it. I think I'll take a walk today.
I've had this experience too. I like doing the work. Claude is good and I do find it useful for brainstorming and some other things, but... I still like doing the work.
Re: Claude Skills
#380I 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…
I would love to understand were this notion of LLM becoming AGI ever came from?
ChatGPT broke upen the dam to massive budget on AI/LM and LLM will probably be a puzzle peace to AGI. But otherwise?
I mean it should be clear that we have so much work to do like RL (which now happens btw. on massive scale because you thumb up or down every day), thinking, Model of Experts, toolcalling and super super critical: Architecture.
Compute is a hard upper limit too.
And the math isn't done either. The performance of Context length has advanced, we also saw other approcheas like a diffusion based models.
Whenever you hear the leading experts talking, they mention world models.
We are still in a phase were we have plenty of very obivous ideas people need to try out.
But alone the quality of whispher, llm as an interface and tool calling can solve problems with robotics and stuff, no one was able to solve that easy ever before.