logoalt Hacker News

jerrygenser • today at 5:26 PM • 1 reply • view on HN

Yes, but people trying new harness improvements like superpowers and this one generate training data which then gets reinforcement learned. It needs to be bootstrapped somehow. If you are an early adopter there's not much to lose by experimenting with harness tweaks.


Replies

flakiness • today at 8:08 PM

If your idea gets trained that'd be a huge win. So it's worth proposing these, and if it' s worthwhile, championing it even if it's your own invention. That's a way to voice your opinion to the labs, effective or not.