Marcus Williams
@Marcus_J_W
Monitoring at OpenAI
Joined November 2024
182 Following 3.7K Followers
🧵 Excited to share the first batch of 6 misalignment reports from OpenAI's new disclosure process for misalignment incidents. We want to be more transparent about the misalignment we see during training, evals and deployment, this is an important step in that direction.
Show more
