Failure mode

Applied to What rationality failure modes are there? by Jacob G-W 1y ago

Applied to Paper: Identifying the Risks of LM Agents with an LM-Emulated Sandbox - University of Toronto 2023 - Benchmark consisting of 36 high-stakes tools and 144 test cases! by Maik Zywitza 1y ago

Applied to The self-unalignment problem by Jan_Kulveit 2y ago

Applied to Don't take bad options away from people by Dumbledore's Army 2y ago

Applied to Is AI Safety dropping the ball on privacy? by markovial 2y ago

Applied to SolidGoldMagikarp (plus, prompt generation) by Jessica Rumbelow 2y ago

Applied to Guarding Against the Postmodernist Failure Mode by Yoav Ravid 4y ago

Applied to A Voting Puzzle, Some Political Science, and a Nerd Failure Mode by Yoav Ravid 4y ago

Applied to Beware the Nihilistic Failure Mode by Yoav Ravid 4y ago

Applied to Failure Modes sometimes correspond to Game Mechanics by Yoav Ravid 4y ago