Hacker News new | ask | show | jobs
by aiauthoritydev2 813 days ago
12% is a very very large number for that kind of problem. I doubt even 0.1% of bug reports in the wild are that well written.
2 comments

Except this is automated, so you could get multiples orders of magnitude more bug filled, so you need to have a very low false positive ratio to avoid being overwhelmed by automatically generated crap (which is basically spam).
Have the LLM rewrite the bug reports.
You'd want three LLMs, one to create the bugs, one to report it, one to fix it. I joke of course but on the other hand this is potentially a worthwhile architecture from a self-training perspective - a bug-creating LLM means your training set size is as big as you want it +/- GAN features.
Why not have LLM write AGI while you're at it
It is and it will!