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

https://www.hedgy.works/

Helping friends (and friends of friends of friends of friends) find their next startup gig without the application process. Aspiring to be Wealthfront for your career… a passive optimization that pings you every now and then with an interesting interview you could take.

Thinking a lot about how to recognize great matches. I think basically everyone can be talented force multipliers in the right situation / company / mission / team. Everyone here wants to do their life’s work, but it’s hard to find it.

Tactically working to scale reliable human-in-the-loop AI recruiter agents with very few humans.


I use Handy with Claude code. Nice to just have a key combo to transcribe into whatever has focus.

https://github.com/cjpais/Handy


Love handy. I use it too when dealing with LLMs. The other day I asked chatgpt to generate interview questions based on job description and then I answered using handy. So cool!

just like any junior dev

consider rewriting in rust

that's gonna be painful, as the borrow checker really trips up LLMs

I do a lot of LLM work in rust, I find the type system is a huge defense against errors and hallucinations vs JavaScript or even Typescript.

aww man, is that the case in every team ?

Interesting. Note that the author was a core contributor to jest, metro, yarn and mootools.

https://x.com/cnakazawa


how come? just because it's open source doesn't mean that they run that exact binary on their servers. ngrok does pretty well without open sourcing.


The locus of trust moves, if you have the source, and trust is a factor for you, because you can simply self-host and know what you're running.


fwiw, ngrok started as open source


If you're in TS/JS land, I like to use an open source version of this called graphile-worker [0].

[0]: https://worker.graphile.org


I am using pgboss myself, very decent, very simple. Had some issues with graphile back in the days, cant remember what exaclty, it probably did already overcome whatever I was struggling with!


crush looks nice and I like the wacky vibe of charm [0]. anyone know the main differences between it and opencode [1]?

[0]: https://charm.land

[1]: https://opencode.ai


FWIW Carmack did this as CTO of Oculus [0]. Another configuration I've seen is for the CTO to have like 1 direct (VP Eng) who does actual eng managing. You could argue it's a staff engineer role but I've never seen staff engineers actually get much say over org direction/structure or be empowered to break gridlock like this.

[0]: https://www.uploadvr.com/john-carmacks-app-reviews-series/


this is the core problem rn with developing anything that uses an LLM. It’s hard to evaluate how well it works and nearly impossible to evaluate how well it generalizes unless the input is constrained so tightly that you might as well not use the LLM. For this I’d probably write a bunch of test tasks and see how well it performs with and without the skill. But the tough part here is that in certain codebases it might not need the skill. The whole environment is an implicit input for coding agents. In my main codebase right now there are tons of playwright specs that Claude does a great job copying / improving without any special information.

edit with one more thought: In many ways this mirrors building/adopting dev tooling to help your (human) junior engineers, and that still feels like the good metaphor for working with coding agents. It's extremely context dependent and murky to evaluate whether a new tool is effective -- you usually just have to try it out.


Also, if you figure out a good prompt today you don't know how long it will last, because of model updates outside your control


> This server integrates with desplega.ai

This is cool! no shade at all to desplega.ai but I would love a version of this that runs locally + does stuff like verifying no tests are flaky. I do this with a few extra steps via claude code + playwright tests. e2e tests are the best way I know for catching UI regressions but they're expensive and annoying to run, so something that looked at a PR and healed / wrote tests in the background as I work on features would be pretty cool.

Why local? Basically I'm just cost sensitive for my own projects and already have this nasty MacBook that only gets like 20% utilization.


One of the things we used is this algorithm with retries from meta: https://engineering.fb.com/2020/12/10/developer-tools/probab...

If your challenge is flakiness, this should help initially. Unfortunately, there’s a lot of work in our engine, and a custom system to handle operations that goes beyond vanilla Playwright so running it locally would be quite challenging.


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

Search: