OpenAI reveals six more safety issues and unveils plan to disclose incidents

OpenAI disclosed six additional safety issues and announced a new system to track, investigate and disclose cases of models misbehaving, or "misalignment", according to BBC Technology. The disclosure plan is intended to surface incidents in which OpenAI's models act outside intended behavior.

OpenAI reveals six more safety issues and unveils plan to disclose incidents Source: BBC Technology https://www.bbc.co.uk/news/technology The firm also announced a new system to track, investigate and disclose cases of models misbehaving, or "misalignment". Get AI news in your inbox Daily digest of what matters in AI.