Comment by prodigycorp
6 hours ago
What we know after the openai incidents is that the RSI process involves models having access to user rollouts via tool calls. What's considered crappy training one year is another year's kompromat!
6 hours ago
What we know after the openai incidents is that the RSI process involves models having access to user rollouts via tool calls. What's considered crappy training one year is another year's kompromat!
No comments yet
Contribute on Hacker News ↗