📢 ICYMI: “There will be systems much smarter than us that may not be aligned with us.” — David Duvenaud
Read our recap and watch the full SRI Seminar on dangerous capability evaluations, AI safety, and alignment:
tinyurl.com/yj9bm5f4
#AI #AIsafety #Alignment #UofT @davidduvenaud.bsky.social
The big picture of dangerous capability evaluations: David Duvenaud at the Seminar Series — Schwartz Reisman Institute
How can we stay in control when AI systems surpass human intelligence? In a recent SRI Seminar, Schwartz Reisman Chair David Duvenaud explored the frontier of AI safety, alignment, and governance , i...
