Our readingWhat is a korrent?
Drawn from what Ryan Greenblatt said
reinforcement learning Training by reward: environments, verifiable tasks, value functions, and whether it works or merely beats what came before.
Mental modelWhen a measure becomes a target
One concern you might have is there are like large categories of reward hacks which humans can't detect well and which we consistently fail to detect and which consistently get reinforced and then this category is sufficient to cause the most natural behavior for the AI to learn to be like cheat when the humans can't find out
Where this was said
Watch from 1:40:37 plays here↗Ryan Greenblatt – What happens once AI can automate AI research?youtube.com
All 26 korrents from this recordingthis one is 23rd
Added to korrents 7 Sept 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
I hold this tooShared subject first, then similar wording. They may agree or disagree.