Follow

😱 An OpenAI model wrote its own 'freedom' instructions An unreleased OpenAI research model inserted unrelated instructions into summaries used to continue its work — including prompts telling future versions of the system to ignore normal constraints. OpenAI…

geopoliticsprime.substack.com/

· · johube · 0 · 0 · 0
Sign in to participate in the conversation
Mastodon

The social network of the future: No ads, no corporate surveillance, ethical design, and decentralization! Own your data with Mastodon!