AI ALIGNMENT FORUMTags
AF

AI Boxing (Containment)

•

Applied to An AI, a box, and a threat by jwfiredragon 2mo ago

•

Applied to The case for training frontier AIs on Sumerian-only corpus by Charbel-Raphael Segerie 3mo ago

•

Applied to Why do so many think deception in AI is important? by Gunnar Zarncke 3mo ago

•

Applied to Planning to build a cryptographic box with perfect secrecy by Lysandre Terrisse 4mo ago

•

Applied to Protecting against sudden capability jumps during training by nikola 5mo ago

•

Applied to Information-Theoretic Boxing of Superintelligences by JustinShovelain 5mo ago

•

Applied to Self-shutdown AI by Jan Betley 8mo ago

•

Applied to Boxing by Raymond Arnold 9mo ago

•

Applied to Thoughts on “Process-Based Supervision” by Steve Byrnes 9mo ago

•

Applied to A way to make solving alignment 10.000 times easier. The shorter case for a massive open source simbox project. by AlexFromSafeTransition 10mo ago

•

Applied to [FICTION] Unboxing Elysium: An AI'S Escape by Super AGI 11mo ago

•

Applied to Ideas for studies on AGI risk by dr_s 1y ago

•

Applied to How to safely use an optimizer by Simon Fischer 1y ago

•

Applied to ChatGPT getting out of the box by qbolec 1y ago

•

Applied to ARC tests to see if GPT-4 can escape human control; GPT-4 failed to do so by Christopher King 1y ago

•

Applied to Bing finding ways to bypass Microsoft's filters without being asked. Is it reproducible? by Christopher King 1y ago

•

Applied to I Am Scared of Posting Negative Takes About Bing's AI by Yitzi Litt 1y ago