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

Show HN: Daemons – we pivoted from building agents to cleaning up after them

charlielabs.ai

Post reply on HN
Print view View original

31–40 of 42 posts

Re: Show HN: Daemons – we pivoted from building agents to cleaning up after them

#31

Post by gogopromptless »

potter098 wrote: post #7

[flagged]

I'm curious if evals of the DAEMONs and replays for debugging are on the roadmap?

I looked but did not see any facility for collecting/managing evals in the Charlie docs.

Docs drift might sound easy for agents but after working on it at https://promptless.ai for about two years, it's been tricker than just "make some skills". We've got an agent that watches PRs and suggests docs changes. Getting the suggestions good enough that doc owners would actually accept them took a fair bit of evals. Non-ai voice matching existing content, and even "simple" act of deciding whether a given PR warrants a docs change at all.

I have benefited greatly from evals catching things (especially as models change) to the point where I'm loath to go back.

Re: Show HN: Daemons – we pivoted from building agents to cleaning up after them

#32

Post by acron0 »

rybosome wrote: post #4
panosfilianos wrote: post #3

Why couldn't these just be callable skills?

Callable skills can’t activate on a schedule or listen for events. Making a daemon which invokes other callable skills is a great use case! I’m an eng on the team that built this, in full disclosure.

> Callable skills can’t activate on a schedule or listen for events

I feel like they can. cron and git hooks have existed for a long time.

Re: Show HN: Daemons – we pivoted from building agents to cleaning up after them

#34

Post by scriptingLLM »

rybosome wrote: post #17
Bootvis wrote: post #16

Earlier quoted context omitted.

I do really like the idea. But pardon my ignorance, but one could quite easily roll this themselves? Script the hooks and fire off a headless agent with a hook specific prompt.

Very fair question. One could build a simple version of this easily - e.g. setup an endpoint that listens for the particular event you are concerned with, and fire off the headless agent with your hook specific prompt - but the amount of work involved to listen for that particular event while filtering out noise and orchestrating the task is actually not trivial. Plus, that involves writing a lot of code. It's really…

Seems the markdown input, code output is a very common theme, I use OpenSoucreContracts(https://github.com/s1ugh34d/osc) to have LLM's build software, but building the harness into the contracts is elegant. Combined with prose I sort of have this. With LLM's and the sandbox life, software generation is coming.

Re: Show HN: Daemons – we pivoted from building agents to cleaning up after them

#37

Post by woud420 »

3uler wrote: post #33

I can not find a description of how it works on the site, magic hands daemons ! Cool story, but what runs when?

tl;dr : https://charlielabs.ai/how-it-works/ and https://docs.charlielabs.ai/daemons

to get started, look at https://docs.charlielabs.ai/installation, but essentially

1) signup with your github login

2) install the CharlieCreates GitHub App on the repos you want Charlie to work in

3) create an issue, tag @CharlieHelps to help you create your first daemon!

the daemon will run on the charlie runtime and follow the watch / schedule conditions you set in your DAEMON.md file

full disclosure: i am part of the engineering team behind this.

Re: Show HN: Daemons – we pivoted from building agents to cleaning up after them

#38

Post by nopointttt »

potter098 wrote: post #7

[flagged]

The pivot framing is refreshingly honest. Most agent startups double down when the next model release makes half their scaffolding obsolete. Drift detection is the right insight though — you end up with more cleanup work than creation work once the agent output volume outpaces your review capacity. Curious how you handle the case where the "drift" is actually a real intent change the human hasn't formalized yet.

Re: Show HN: Daemons – we pivoted from building agents to cleaning up after them

#39

Post by usernametaken29 »

I might try your tool but from my experience PR review and the general state of AI improvement for code is just fu*ing awful. Oh I forgot to ident three lines of code thanks buddy how about this massive memory leak instead that’s of actual value to anyone?

Re: Show HN: Daemons – we pivoted from building agents to cleaning up after them

#40

Post by viktorianer »

Bootvis wrote: post #16
rybosome wrote: post #4

Earlier quoted context omitted.

Callable skills can’t activate on a schedule or listen for events. Making a daemon which invokes other callable skills is a great use case! I’m an eng on the team that built this, in full disclosure.

I do really like the idea. But pardon my ignorance, but one could quite easily roll this themselves? Script the hooks and fire off a headless agent with a hook specific prompt.

[dead]
Post reply on HN