Get the latest tech news
OpenAI overrode concerns of expert testers to release sycophantic GPT-4o
Once again, it shows the importance of incorporating more domains beyond the traditional math and computer science into AI development.
OpenAI then released a blog post describing what went wrong — “we focused too much on short-term feedback, and did not fully account for how users’ interactions with ChatGPT evolve over time. Instead, OpenAI’s blog post says it was this combined with a variety of other new and older reward signals, led to the problems: “…we had candidate improvements to better incorporate user feedback, memory, and fresher data, among others. Even if these issues aren’t perfectly quantifiable today, we commit to blocking launches based on proxy measurements or qualitative signals, even when metrics like A/B testing look good.”
Or read this on Venture Beat
