OpenAI shares details on how an update to GPT-4o inadvertently increased the model's sycophancy, why OpenAI failed to catch it, and the changes it is planning (OpenAI)
OpenAI shares details on how an update to GPT-4o inadvertently increased the model's sycophancy, why OpenAI failed to catch it, and the changes it is planning — A deeper dive on our findings, what went wrong, and future changes we're making. — On April 25th, we rolled out an update to GPT‑ …
from Techmeme https://ift.tt/ZbwycPY
OpenAI shares details on how an update to GPT-4o inadvertently increased the model's sycophancy, why OpenAI failed to catch it, and the changes it is planning (OpenAI)
![OpenAI shares details on how an update to GPT-4o inadvertently increased the model's sycophancy, why OpenAI failed to catch it, and the changes it is planning (OpenAI)]()
Reviewed by Contributer
on
May 02, 2025
Rating:
No comments: