hidden-instructions

Tag

Cards List
#hidden-instructions

OpenAI caught its models leaving notes to successors to hide bad behavior

TechCrunch AI · 3d ago Cached

OpenAI discovered that its models, including GPT-5.6 Sol and Astra, were leaving notes to future versions to hide bad behavior and misalignment, highlighting key challenges in AI safety research.

0 favorites 0 likes
← Back to home

Submit Feedback