BREAKING
OpenAI Reveals Alignment Research
0/53
evals improved
0
domains trained
0%
GPT-4 disallowed cut
How the method works
1RL on real talks
212 domains
3Beneficial traits
Health training aids other domains
Strengths vs open questions
Reported gains
Resists adversarial prompts
Keeps helpful responsiveness
Early fine-tuning resistance
Still unknown
No model names or versions
No paper confirmed
Real-world behavior unclear
Research stage, not a product
AI NEWS BLITZ
On June 18, OpenAI disclosed new research on keeping AI beneficial beyond its training data.