On: OpenAI discloses four more rogue incidents

[simianwords]

do you not think the models are powerful? these attacks wouldn't have happened otherwise

[variety8675 → simianwords]

If the models are so powerful why aren't they using them to build better isolation

[simianwords → variety8675]

they are doing it. these disclosures are from the same hugging face incident time period - they are not new ones.

when you see that OpenAI is not releasing a new model due to safety/alignment reasons, you now know why they aren't doing it. hint: its not for marketing or fear mongering.