12 points bradleygibbs 19 hours ago 8 comments

bradleygibbs 19 hours ago | parent

Author here. This is a detailed (8,000+ word, plus 2 companion pieces) walk-through of building loops for code generation and verification, complete with artifacts and detailed explanations to allow you to implement any of these techniques.

We walk through building: - an evaluation contract, evaluator and stopping conditions to minimize bugs - establishing an environment and priming AI to produce production-quality tests and code - detecting and correcting common AI failure modes - building a learning loop to monitor and improve all phases.

I'd love to get your feedback!

Brad

Neywiny 10 hours ago | parent

I think it's just too much. Honestly it feels like the whole thing could be a tight 100 line bash script. The diagram at the start didn't look too complicated

dhruvagoyal 1 hour ago | parent

it's full of slop, even if there is something you were hoping to convey, it's lost in 8,000+ words. In this LLM world, less is more.

docheinestages 1 hour ago | parent

> (8,000+ word, plus 2 companion pieces)

I appreciate the idea, but I doubt you wrote or actually read the whole thing. There's no point in trying to impress people with complexity. The art of writing is to convey your message with the least amount of text, while retaining maximum information, and making it easy to read.

I could've written what I wrote above with 8,000+ words too.

tomaac_ 1 hour ago | parent

Thank you, Mr. AI. Seriously, this slop is worthless and you burned all those tokens for nothing.

genxy 58 minutes ago | parent

You are not the author, but merely the driver of the slop dozer.

duhhhhh1212 9 hours ago | parent

mobilejdral 1 hour ago | parent

Sure, could probably be made shorter, but the content was more valuable than some pangram score. I found it useful to read as it discusses a problem currently facing teams.