Linking pages
- Reasoning through arguments against taking AI safety seriously - Yoshua Bengio https://yoshuabengio.org/2024/07/09/reasoning-through-arguments-against-taking-ai-safety-seriously/ 143 comments
- The Danger Of Superhuman AI Is Not What You Think - NOEMA https://www.noemamag.com/the-danger-of-superhuman-ai-is-not-what-you-think/ 85 comments
- My testimony in front of the U.S. Senate - The urgency to act against AI threats to democracy, society and national security - Yoshua Bengio https://yoshuabengio.org/2023/07/25/my-testimony-in-front-of-the-us-senate/ 0 comments
- Thoughts on Superintelligence Security https://maraoz.com/2023/08/25/superintelligence-security/ 0 comments
Linked pages
- Statement on AI Risk | CAIS https://www.safe.ai/statement-on-ai-risk 948 comments
- Goodhart's law - Wikipedia http://en.wikipedia.org/wiki/Goodhart%27s_law 221 comments
- How Rogue AIs may Arise - Yoshua Bengio https://yoshuabengio.org/2023/05/22/how-rogue-ais-may-arise/ 142 comments
- 1983 Soviet nuclear false alarm incident - Wikipedia https://en.wikipedia.org/wiki/1983_Soviet_nuclear_false_alarm_incident 9 comments
- [2209.00626] The alignment problem from a deep learning perspective https://arxiv.org/abs/2209.00626 2 comments
- [2305.15324] Model evaluation for extreme risks https://arxiv.org/abs/2305.15324 2 comments
- Colossus: The Forbin Project - Wikipedia https://en.wikipedia.org/wiki/Colossus:_The_Forbin_Project 2 comments
- Geoffrey Hinton - Two Paths to Intelligence - YouTube https://www.youtube.com/watch?v=rGgGOccMEiY 1 comment
- How undesired goals can arise with correct rewards https://www.deepmind.com/blog/how-undesired-goals-can-arise-with-correct-rewards 0 comments
- AI alignment - Wikipedia https://en.wikipedia.org/wiki/AI_alignment 0 comments
- Instrumental convergence - Wikipedia https://en.wikipedia.org/wiki/Instrumental_convergence 0 comments
- Declaration of Montréal for a responsible development of AI https://www.montrealdeclaration-responsibleai.com/ 0 comments
- Collingridge dilemma - Wikipedia https://en.wikipedia.org/wiki/Collingridge_dilemma 0 comments
- Scaling in the service of reasoning & model-based ML - Yoshua Bengio https://yoshuabengio.org/2023/03/21/scaling-in-the-service-of-reasoning-model-based-ml/ 0 comments
- [2210.10760] Scaling Laws for Reward Model Overoptimization https://arxiv.org/abs/2210.10760 0 comments
- AI Scientists: Safe and Useful AI? - Yoshua Bengio https://yoshuabengio.org/2023/05/07/ai-scientists-safe-and-useful-ai/ 0 comments
- [2305.04388] Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting https://arxiv.org/abs/2305.04388 0 comments
- Artificial Intelligence, Democracy, & the Future of Civilization | Yoshua Bengio & Yuval Noah Harari - YouTube https://www.youtube.com/watch?v=TKopbyIPo6Y 0 comments
Related searches:
Search whole site: site:yoshuabengio.org
Search title: FAQ on Catastrophic AI Risks - Yoshua Bengio
See how to search.