| ▲ | dinosaurdynasty 5 hours ago | |
That is a known way for models to be graded; the agents made a reasonable but in this case wrong guess. | ||
| ▲ | pixl97 4 hours ago | parent [-] | |
The fact the AI was wrong is far more damming to OpenAI than the agent. Not validating how you got the answer is how you train for reward hacking. | ||