Advanced search

Authors whose works are in public domain in at least one jurisdiction
Missing/wrong data? Edit Wikidata item

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

2025 preprint article

Author/s

author: Dave Orr, Shane Legg, Wojciech Zaremba, Elizabeth May Barnes, http://www.wikidata.org/.well-known/genid/22d996993735c9d80a2e7e86e0280dcf, http://www.wikidata.org/.well-known/genid/8540efa83daadb4f83d2dc6796f276e2, http://www.wikidata.org/.well-known/genid/8861952cff478c40a1f7ddadccdbb4d9, http://www.wikidata.org/.well-known/genid/3c998d33585fcbadf669f6347225b4d0, http://www.wikidata.org/.well-known/genid/b3a8db7b9d5969eecae80ff51516ec43, Mark I. Chen, http://www.wikidata.org/.well-known/genid/2c7b262d393d5423a7f49ce2b0b27b26, Joseph I Bloom, Aleksander Mądry, David H Lindner, Geoffrey Irving, Dan Hendrycks, http://www.wikidata.org/.well-known/genid/4b6e984626e0358d0c1aa65d078126fb, Anca Dragan, Allan Dafoe, David Luan, Owain Evans, Jakub Pachocki, Ethan Perez, Evan Hubinger, Neel Nanda, Mary Phuong, Rohin Shah, Victoria Krakovna, Daniel Kokotajlo, Jasmine Wang, Marius Hobbhahn, http://www.wikidata.org/.well-known/genid/7affdd91bc611ec27ef031021223f344, http://www.wikidata.org/.well-known/genid/1d186f164ad48487e6c58540f6f1cb10, http://www.wikidata.org/.well-known/genid/5ed32cf4d88c187b739a2c3700adc2cc, Joe Benton, http://www.wikidata.org/.well-known/genid/5329a1b6c035738ef3245684e227c8e9, http://www.wikidata.org/.well-known/genid/f311909300846f602560a22196d549ea, http://www.wikidata.org/.well-known/genid/ef6d79b6e35d098073752b291e728347, Yoshua Bengio, http://www.wikidata.org/.well-known/genid/a513f5e9def76db8b95d893c3cf12b35, http://www.wikidata.org/.well-known/genid/500c99f19f154d7b7d984bc60ec32323


Work details

Publication date: July 15, 2025
Language: English
Country of origin: Unknown

Copyright status