Hacker Newsnew | past | comments | ask | show | jobs | submit | zimbatm's commentslogin

Isn't the point of OpenClaw that the agent can modify itself?

Self modifying part is through skills:

Assistant -> Skill -> Script.

As you keep modifying or adding capabilities, it’s the script that gets modified. Atleast that’s how OpenClaw works, I’m not sure how Moltis implements self-modifying part.


If you run it with a cheaper model or just once in a while, it will write sometjing unexpected into its config json, restart and crash. Happens every few days. I learned to back up the config the hard way

This is what I'm interested in knowing. Just how much can it modify if it's a static binary? Can it modify it's own agents.md etc?

It can modify everything, because while it's a single binary and that makes it easy for installation, there are things stored outside that binary. The memories, the skills, the config etc. But you can do everything from the UI and you don't need to bother, it will be all automatic.

Just added it to our inventory. For those of you using Nix:

    nix run github:numtide/llm-agents.nix#mistral-vibe
The repo is updated daily.


This is such a cool project. Thanks for sharing.


Thanks! Playing with packaging automation is actually quite fun.


Gerrit is doing this with NoteDB. Backups are just one git clone away.

See https://gerrit-review.googlesource.com/Documentation/note-db...


This should have been CONTRIBUTING.md all along.

The content of the AGENTS.md is the same as what humans are looking for when contributing to a project.


The most effective argument I have for getting other developers to comment their code is "The agent will read it and it will give better suggestions".

Truly perverse, but it works.

I agree with you... but the reality is that there's a wide contingent of people that are not capable of understanding "people don't know the same things as me". So they need some other reason.


It's made my project documentation so much better. If I write out really good acceptance criteria, 9 times out of 10 I can point Claude at the ticket and get a workable (if unpolished) solution with little to no supervision.


[flagged]


you've not had your "oh shit" moment yet?


They understand it just fine; they are acting selfishly, because it does not benefit them. Helping the coding agent does.


They really might not understand it fully. That's very much in line with my understanding of how autism works.


several ironies here:

1) an AI agent is less likely to notice than even a junior is when the docs are out of date from the code

2) AI boosters are always talking about using language models to understand code, but apparently they need the code explained inline? are we AGI yet?

3) I frequently hear how great AI is at writing comments! But it needs comments to better understand the code? So I guess to enable agentic coding you also have to review all the agents' comments in addition to the code in order to prevent drift

HOW IS ANY OF THIS SAVING ME TIME


Well... Yah. For the record I'm saying this to trick humans into making better comments for humans. It is very difficult to convince people to do this otherwise, in my experience.

buuut...

I will also mention that these agent files are typically generated by agents. And they're pretty good at it. I've previously used agents to dissect unfamiliar code bases in unfamiliar languages and it has worked spectacularly well. Far far FAR better than I could have done on my own.

I have also been shocked at how dumb they can be. They are uselessly stupid at their worst, but brilliant at their best.


Think of it like it's saving future you time if you just let the AI centipede feed off of you. Surely it'll eventually regurgitate perfect code.


I don’t think they serve the same purpose. Most of the instructions I have for an agent won’t apply to a human. It’s mostly around the the requirements to bootstrap the project vs what I’d ask for a human to accept their pull request.


I think semantically this is true, but the way humans and agents handle context, at the moment, is different enough to warrant a separate structure.


Yeah I can't find any example in an AGENTS.md that isn't useful information for a human. "Cluttering" a README.md is a silly justification.


Nah, My standard for what I write for humans is 100x than the slop I spew for robots.

Also, you don’t even address their point.


Arguably, contributors are human agents. ;)


Dude, this is such a good point.



Thanks! Do you have experience using it? I'm quite nervous on using node CLT because the dependencies will always end up destroying the project and seeing it hasn't been updated in 5 years does not instill confidence.

The golang project looked better because at least the golang project provides a binary.


I haven't used it extensively, but it works. I don't think it necessarily needs any updates since the underlying tech is stable.


Quality animated SVGs is even better:

https://github.com/marionebl/svg-term-cli


The amount of information the SVG must store to represent the animation actually crashed the application creating it. There’s too much going on in TTE animations.


Yes, you can target VMDK, AMIs, Azure, ...

`nixos-rebuild build-image --image-variant vmware`

See https://nixos.org/manual/nixos/stable/#sec-image-nixos-rebui...


One thing I miss the most when writing Markdown is this formula experience you get in Excel. Jot something down, get the result. Then link it to another block.

There are tools like Jupyter notebooks that have all the functionalities, but their file format isn't very readable or diffable using standard terminal tools.

A while back I wrote https://github.com/zimbatm/mdsh to explore the space. Voiden.md looks like a fancier version of that.


You could technically add mdsh to the Voiden terminal, and now the whole thing is fully markdown haha. Curious, what did you learn from exploring it?


That I wasn't very good at Rust :-D

My assumption was that a tool like this will make it easier to keep the README.md in sync while the project evolves. Think of a `--help` section. That assumption holds true to me.

You can see it in action for example here: https://github.com/numtide/treefmt-nix?tab=readme-ov-file#su...

The best part is that it makes it easy to keep the README.md in sync when the project evolves. Just add it to the CI


Why would the book be worth buying tough. If AI can generate a fresh new one just for you?


I don't know. It's a question relevant to all generative AI applications in entertainment - whether books, art, music, film or videogames. To the extent the value of these works is mostly in being social objects (i.e. shared experience to talk about with other people), being able to generate clones and personalized variants freely via GenAI destroys that value.


Since Chrome's engine is used by Edge, Opera, Brave, etc.. Probably the best move is to become a non-profit and have all those organizations chip in.

The main reason even Microsoft gave up and rebased their browser on top of Chrome is because of the breakneck speed at which Google introduces new standards and features to the ecosystem. Having them be forced to slow down might be a good thing for browser diversity and the future of the Internet.


Or maybe because Chromium is pretty good, open-source and there's nearly no upside to reinventing the wheel?

If Mozilla would fork Chromium now and base Firefox on their fork I would switch from Brave. The engine simply technically superior.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: