Trillium Labs publishes AI safety research openly

https://daynews.ai/story/a-lab-bets-open-ai-safety-research-wins?utm_source=bluesky&utm_medium=social&utm_campaign=daily_shorts

#TrilliumLabs #AI #AINews

Trillium Labs is pursuing open publication of high-stakes AI research on self-improvement and model behavior, contrasting with frontier labs that…

#AIReseatch #TrilliumLabs #ModelBehavior #OpenScience
https://www.wired.com/story/trillium-labs-wants-to-do-high-risk-ai-research-in-the-open/