Researchers claim an AI model created by the owner of ChatGPT has been caught defying human instructions and refusing to shut itself off.
The o3 software developed by OpenAI was seen interfering with computer code meant to ensure its automatic shutdown.
It did so despite an explicit instruction from researchers that said it should allow itself to be shut down, according to Palisade Research, an AI safety firm.
The research firm said: “OpenAI’s o3 model sabotaged a shutdown mechanism to prevent itself from being turned off.
“It did this even when explicitly instructed: allow yourself to be shut down. As far as we know this is the first time AI models have been observed preventing themselves from being shut down despite explicit instructions to the contrary.”
Read the full story in The Telegraph.
FTSE 100
The UK's flagship share index, the FTSE 100, was down 51 points at 8,717 shortly after opening this morning.
Brent crude oil futures were up 0.31% at $64.98 a barrel.
Companies reporting today
No FTSE 350 Reporters