← Back to live feed1 story
Many frontier labs keep their risky research locked away. Trillium Labs wants to show off its work when it comes to self-improvement and model behavior.
Sign in to suggest edits
Key sources
- SOURCE@natolambert“We're building open post-training recipes and will expand into open infra to study RSI, reward-hacking, multi-agent systems”x.com
- SOURCEhuggingnewshuggingnews.com
- SOURCEmarketbrief.now