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

as a back end guy, UI is a savior when it comes to UI, it's not perfect but it's much better than what I can code on my own.

reply


if it's a device provided by your company, it's very likely it'll have some spyware on it.

reply


I got a very similar email too.


  Location:South Florida
  Remote: Yes, or office/hybrid
  Willing to relocate:No
  Technologies: 7 years of experience working with Nodejs, JS/Typescript, Reactjs, AWS SQL, ElasticSearch etc. Also some hobbist knowledge of Go.
  Résumé/CV:
  Email: jonagerdev@gmail.com


roc lang looks very interesting, I see they use a lot of Zig and Rust, very unusual combo I think.


I think they are switching from Rust to Zig. I don’t recall exactly, but they talked about it in a video where the creator of Roc interviewed the creator of Zig.

https://www.youtube.com/watch?v=w74rC-6caxE


thanks, will watch it later


I also can't wait for the day I retire, I got laid off recently, so that sets things back for me for now, but as soon as I get another job, it's all about saving to escape this damn rat race. I hope you can retire soon too.


if you're in the US, ACA is an option, but it'll be expensive if you don't qualify for any subsidies.


what's a big project built with D? I feel it gets mentioned a lot on hackernews but I've never run into any project using it in the wild.


Flutter


Elixir is missing static types though, it's hard to go back to work on dynamic languages.


Hopefully, it's coming.

https://elixir-lang.org/blog/2023/06/22/type-system-updates-...


maybe it's dumb question, but how do you feed the results of one agent to another? do you copy and paste manually? or how do you do it programmatically?


When I pair Claude and Codex, I use claude-co-commands [0] to drive from Claude and talk to Codex via MCP. Lately I've found Codex has been far more consistent for my specific projects, so I've just been almost entirely inside Codex. YMMV

[0] https://github.com/SnakeO/claude-co-commands


Yea I'll take the review feedback from one, validate it, and then copy/paste it into the other session saying like, "hey I got this feedback, what do you think?" So I'm not even telling the other AI the feedback is valid, I want it to independently validate it. Often the feedback is not like a bug, but a red flag, design consideration, or trade off.

Often depending on how complex the feedback, I'll do it one at a time addressing each one individually. And after the feedback is addressed, I'll go back to the AI that generated the feedback and say like, "I handled 4/5 items you found, can you double check."

It's similar to handling PR feedback, where you do it, validate it, but then still have to submit it for peer review.


Having the agents write their plans into text files and iterating on those works reasonably well.


Just switch models whenever you want with the menu at the bottom of the chat window in Cursor.

And maybe don't use tools that lock you into one model?


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

Search: