Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Towards a harness that can do anything

eardatasci.github.io

Post reply on HN
Print view View original

1–10 of 121 posts

Re: Towards a harness that can do anything

#3

Post by _superposition_ »

I really like this idea and the way you mapped the concepts to unix primitives. Indeed llms are already "unix native". I've been experimenting with similar event driven workflows using k8s primitives but that's one level up the stack. This makes a whole lot of sense to me in terms of organizing a shared mental model. Will definitely check it out. Thanks for the good work.

Re: Towards a harness that can do anything

#5

Post by ardatasci »

_superposition_ wrote: post #3

I really like this idea and the way you mapped the concepts to unix primitives. Indeed llms are already "unix native". I've been experimenting with similar event driven workflows using k8s primitives but that's one level up the stack. This makes a whole lot of sense to me in terms of organizing a shared mental model. Will definitely check it out. Thanks for the good work.

thanks a lot! let me know what you think -- i'd love to share ideas with people doing similar stuff!

Re: Towards a harness that can do anything

#7

Post by _superposition_ »

ardatasci wrote: post #5
_superposition_ wrote: post #3

I really like this idea and the way you mapped the concepts to unix primitives. Indeed llms are already "unix native". I've been experimenting with similar event driven workflows using k8s primitives but that's one level up the stack. This makes a whole lot of sense to me in terms of organizing a shared mental model. Will definitely check it out. Thanks for the good work.

thanks a lot! let me know what you think -- i'd love to share ideas with people doing similar stuff!

I do have a gripe already... The readme says macos, however as of yet I don't see the actual dependency. Sort of defeats the *nix spirit as well, no?

Re: Towards a harness that can do anything

#8

Post by PhunkyPhil »

FrattB wrote: post #4

Why are we not just using Claude Code or Codex on our machine and using this thing? Real question...

I'm kind of in the same boat and it's been pestering me for months. Every agent is simply a less capable Claude Code.

If it had a lossless, massive context window (100m-1b tokens), then it will squash everything. Give it bash + r/w and it can in theory /goal anything.

I think there's something to be gained in a production environment be siloing agents for reproducebility/auditability, but I suspect that will go away in the future.

There's that video of a silly demo someone made of an OS that was just nested copilot instances that generated the HTML of each window, which allowed you to do whatever you could imagine. It was seen as silly because it was, but that seems truly transformative.

Re: Towards a harness that can do anything

#9

Post by ardatasci »

_superposition_ wrote: post #7
ardatasci wrote: post #5

Earlier quoted context omitted.

thanks a lot! let me know what you think -- i'd love to share ideas with people doing similar stuff!

I do have a gripe already... The readme says macos, however as of yet I don't see the actual dependency. Sort of defeats the *nix spirit as well, no?

Yeah, a little... I was mostly building this for myself so I didn't really think about other platforms but I'll get to it asap :)

Re: Towards a harness that can do anything

#10

Post by ardatasci »

_superposition_ wrote: post #7
ardatasci wrote: post #5

Earlier quoted context omitted.

thanks a lot! let me know what you think -- i'd love to share ideas with people doing similar stuff!

I do have a gripe already... The readme says macos, however as of yet I don't see the actual dependency. Sort of defeats the *nix spirit as well, no?

Actually I was initially going to put this on my Arch machine because utilizing FUSE made a lot of sense to me, but I realized that I use my mac a lot more often so I suppose that's what caused that choice.
Post reply on HN