@trikcode Failure is an excellent way to learn. Knowing what doesn’t work through hands-on experience is just as valuable. You just have to be able to stop and say “wait this ain’t right”
@davidfowl I was doing this for an android app and it’s incredible. Not only are they good at spotting issues, they’ll tell you exactly what might be causing it *and* explain why it’s happening and how to avoid it.
Such a great time to learn even though an agent might do the typing for you
@davidfowl@sinclairinat0r@JamesNK Seems useful for helping an agent find which PR caused a regression. More descriptive than commits, less verbose than diffs
@davidfowl@techgirl1908 I combat this with strict adherence to well known design patterns. Where before I was a little more relaxed, today code has a correct and incorrect place to exist. The only way to avoid duplicate code is to make it so the LLM will always try to put the same code in the same spot.
@sama The compaction and code quality differences between Codex and competitors is night and day. For shipmas, all I want is a mobile app that tunnels to a codex cli or the app, though 🙏
@davidfowl I was using Aspire + Dapr for a chat app experiment and it was wonderful. Being able to run both python and dotnet services along with all of the arbitrary supporting infrastructure like redis/postgres with F5 was a dream.
No dedicated devops. Rotating responsibility. A black box can’t be optimized or innovated on.
Enlightened developers make a point to be well versed in every aspect of the system they work on. Particularly in the cloud where the choices you make on how you deploy your application directly impacts the architecture.
Makes me sad to see developers toss things over the fence.
@theo Turns out that LLMs are really good at writing prompts too.
My favorite workflow is having an LLM help me write a detailed spec and then making a whole new context to work through the spec one section at a time.