61–70 of 74 posts
Earlier quoted context omitted.
A second renaissance? The entire time internet had been running on CLI. All modern services relying om containers rely on images based on CLI. There is no renaissance needed because it never stopped.
Sure, server-side. What I am talking about is user-facing programs. That is why I mentioned codex as an example.
Earlier quoted context omitted.
Yeah, people seem to forget one of the L's in LLM stands for Language, and human language is likely the largest chunk in training data. A cli that is well designed for humans is well designed for agents too. The only difference is that you shouldn't dump pages of content that can pollute context needlessly. But then again, you probably shouldn't be dumping pages of content for humans either.
I also feel like it's just a matter of time until someone cracks the nut of making agents better understand GUI's and more adept at using them. Is there progress happening in that trajectory?
There was a recent Hackernews post which had a novel approach about making agents interact with GUI/computer-use
https://news.ycombinator.com/item?id=47125014: The First Fully General Computer Action Model : https://si.inc/posts/fdm1/
Hope this helps
Earlier quoted context omitted.
Claude Code, at least, will only load a SKILL.md file into context when it’s invoked by the user or LLM itself, i.e. in demand.
Claude will load the name and description of each enabled skill into context at startup[0]; the LLM needs to know what it can invoke, after all. It's negligible for a few skills, but a hundred skills will likely have some impact, e.g. deemphasizing other skills by adding noise. [0]: https://platform.claude.com/docs/en/agents-and-tools/agent-s...
Also, the author specifically mentions OpenClaw in the example skill frontmatter, so I'm wondering if their workflow even involves CC.
Right now a lot of the focus is on getting them to execute tasks reliably. But the harder problem might be reconstructing what actually happened later, why a decision was made, what context the agent had, and how you audit or override it if something goes wrong.
Feels like autonomy is moving faster than the accountability layer around it.
Earlier quoted context omitted.
Sure, server-side. What I am talking about is user-facing programs. That is why I mentioned codex as an example.
Guess I'm still confused, codex is a user-facing program?
If AI agents need CLIs, then whats stopping them from using APIs directly. I see CLIs as good wrappers over APIs, and nothing more. What more will CLIs provide which `curl -X POST` can't/won't provide?
John Carmack made this observation (cli-centred dev for agents) a year ago: LLM assistants are going to be a good forcing function to make sure all app features are accessible from a textual interface as well as a gui. Yes, a strong enough AI can drive a gui, but it makes so much more sense to just make the gui a wrapper around a command line interface that an LLM can talk to directly. https://x.com/ID_AA_Carmack/sta…
Thanks for sharing these contents. They are very interesting. I found "making all app features accessible from a textual interface..." actually quite challenging in cerntain domains such as graphics related editing tools. Though many editing functions can be exposed as CLI properly, but the content being edited is very hard to be converted into texts without losing its geometric meaning. Maybe this is where we truly…
For decades now, pro design print shops have required text files describing the design to print from.
And as every Danish pelican cyclist knows, graphics are their most scalable as text vectors.
Inkscape does fine with these.