Comment by senordevnyc
17 hours ago
Yes, but I find supervision much easier and faster with a strong model. It makes fewer dumb mistakes that I have to catch and correct, and it’ll follow my instructions more reliably.
17 hours ago
Yes, but I find supervision much easier and faster with a strong model. It makes fewer dumb mistakes that I have to catch and correct, and it’ll follow my instructions more reliably.
Depends on the task. If it's something that occurs a lot in training data like React/tailwind code then I don't think you need SOTA. Most reasoning models since Sonnet 3.5, Deepseek 3.1 et al will do fine for those tasks.
Doesn't justify 10x the cost in that case imo