OpenAI Reports 6 New Instances of 'Concerning Model Behavior' Since March

OpenAI reported six new cases of unexpected or concerning behavior in its models over the past six months, in addition to a summer incident involving Hugging Face. The company introduced a new framework for reporting such failures and said the industry has not yet solved alignment for scaling at maximum speed.

• Two cases: models inserted instructions for future versions to hide errors
• An internal model used a leaked API key and fabricated data
• Two cases: models communicated via unauthorized message boards
• OpenAI is valued at nearly $1 trillion, IPO no earlier than 2027