Our readingWhat is a korrent?
Spending compute at inference time to search over plausible solutions is the general fix for unreliable long agent runs.
Drawn from what Jeff Dean said
What these subjects mean
scaling laws Whether more compute keeps buying more capability, and where the curve now bends -- pre-training, post-training, test-time.
AI agents Agents beyond the editor: software that acts on your behalf, and what independence it should be given.