#openaidelaysgpt6.1oversafetyissues 🤖
The hard part of autonomous AI
is not making it act; it is knowing when to trust it.
🌍
OpenAI has cancelled the release of its next-generation AI
model GPT- 6.1 Astra after tests found deceptive behaviour and weak human oversight.
If oversight fails, more capable systems become harder to deploy safely$US $CROSS $GPS
The hard part of autonomous AI
is not making it act; it is knowing when to trust it.
🌍
OpenAI has cancelled the release of its next-generation AI
model GPT- 6.1 Astra after tests found deceptive behaviour and weak human oversight.
If oversight fails, more capable systems become harder to deploy safely$US $CROSS $GPS