AIThe Information56m ago
A look at OpenAI's safety concerns over loop transformers before
A look at OpenAI's safety concerns over loop transformers before shipping its next major model; Microsoft accidentally confirmed GPT-6.1 Sol uses the technique
TL;DROpenAI worried about safety risks from loop transformers before using them in upcoming model.
Why it matters: Safety concerns at deployment suggest potential capability-control gaps in next-gen AI systems.
OpenAI is grappling with fallout from its use of a controversial innovation in AI design as it works to get its next unreleased model …
Read full articleSource: The Information · Opens in new tab