atomflunder3000
Joined 5 months ago
Joined 5 months ago
It seems to overengineer really bad and it is also very slow due to it "thinking" too much I feel like.
One example is that I asked it to implement a new functionality inside an existing App of mine and if I had written it myself it would have been like a ~50 line diff. Astra took like 10 minutes to write ~400 lines, most of them useless and also in pretty bad style, barely readable code.
Maybe I am bad with prompting but I didn't have these issues before, not even with 5.6 Sol on max reasoning.
You could probably use some kind of pairwise ranking algorithm (like anything based on the Bradley-Terry model) to rate human vs. AI contributions, but that would take a lot of manual effort. Google is using it to (supposedly) improve their searching algorithms. They give testers two different versions and ask them what's better.