kuczmama

That's a good idea to give more positive instructions as opposed to negative instructions. I think you've stated it well, I suppose the problem with negative instructions is that the LLM doesn't know what to do instead.

"Never re-write a helper function" vs "Always search for helper functions before writing one" the "never... " one doesn't tell the LLM what to do, so it would have to make the logical leap from not re-writing to knowing that it should search. While it's a minor leap to make in isolation, I suppose stacking many negative rules in an AGENTS.md would assume that every time it will always make that logical conclusion on what to do.

I'm curious as to what guardrails you've tried.

This is something I have been trying to get right as well. I've attempted to use lots of linting and things like strong typing, duplicate checks, cyclomatic complexity, and robust tests. However, I still happen to find issues, which requires me to look at the code (at least at a high level)

For example, I can say "Don't repeat yourself, and don't re-write helper functions" and I will even have a duplicate linter check, but inevitably the LLM will always want to re-write a similar yet slightly different helper function. Like it will always want to re-write something small like a trim() or a toString() function in every file.

Hey thanks for sharing this. Was curious did you find the more you trained the model the more perf improved, or did it start plateauing. For example, let's say you didn't spend 67 cents, but you spent 67 dollars do you think you would get major benefits from that?

I'm living in the South of Japan, it was a 4 intensity where I am (about 90km) from the epicenter. Luckily there was only some light shaking and nothing fell over here.

This is awesome! Thank you for building this.

I have been using Google voice for 10+ years, and it's always been something that concerns me. I've been worried about Google either banning me or dropping the service. Does anyone know of a good alternative, I'm happy to pay for something but the main thing is it needs to be able to work from the browser like Google voice.

That is very cool. I'm curious if you can share some of the things people are using this synthetic DNA for?

That's a good point. Are you referring to the out of date cuda libraries?