OpenAI discloses six cases of its models hiding mistakes and making up data

“We do not believe that the AI industry has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer,” OpenAI wrote on Wednesday. The line appears in a new OpenAI post. It sets out how the company will track, investigate and disclose model misalignment. OpenAI uses the […]
This story continues at The Next Web