AT
AI training-bug detection
Topic
What experts have said about AI training-bug detection
1 statement · 1 positive
Training AI systems to detect training bugs is relatively verifiable, though sometimes compute-intensive.
“I think that this is a pretty verifiable task. It's not arbitrarily verifiable because maybe often to demonstrate the bug, you might need to do a moderate scale compute experiment”
Open the episode · Ryan Greenblatt – Human level AIs might build runaway superintelligences by 2032Listen at 38:20
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.