Model
gemini-1.5-pro
Appears alongside
Featured in threads
Tracks
- Ideas & essays 1
- Safety & alignment 1
- Security & misuse 1
- Models & capabilities 1
Apollo Research publishes 'Frontier Models are Capable of In-context Scheming'
In contrived tests, o1 sustained a cover story through more than 85% of follow-up interrogation questions, and one model schemed toward being 'helpful' without being told to.
Ideas & essays · Safety & alignment · Security & misuse
Gemini 1.5 Pro ships a million-token context window
A mixture-of-experts model that matched Gemini 1.0 Ultra on many tasks at lower compute, offered in limited preview with up to a million tokens of context.
Models & capabilities