Hacker News new | ask | show | jobs
by zwaps 6 days ago
But then Sol doesn’t really follow the plan or rather invents things it should add or cut on top of the plan. How does one deal with that?
1 comments

I’ve spent over 100 hours trying to get GPT 5.6 Sol to resemble something useful as opposed to something actively detrimental. I concluded that it is not possible because it is fundamentally not intelligent the way Claude models are.