LESSWRONGTags
LW

AI Risk Concrete Stories

•

Applied to LifeKeeper Diaries: Exploring Misaligned AI Through Interactive Fiction by Gunnar_Zarncke 12d ago

•

Applied to "If we go extinct due to misaligned AI, at least nature will continue, right? ... right?" by plex 6mo ago

•

Applied to Brainstorming: Slow Takeoff by David Piepgrass 10mo ago

•

Applied to "Humanity vs. AGI" Will Never Look Like "Humanity vs. AGI" to Humanity by Thane Ruthenis 1y ago

•

Applied to Challenge proposal: smallest possible self-hardening backdoor for RLHF by Christopher King 1y ago

•

Applied to Catastrophic Risks from AI #6: Discussion and FAQ by Dan H 1y ago

•

Applied to Catastrophic Risks from AI #5: Rogue AIs by Dan H 1y ago

•

Applied to Catastrophic Risks from AI #4: Organizational Risks by Dan H 1y ago

•

Applied to Catastrophic Risks from AI #3: AI Race by Dan H 1y ago

•

Applied to Catastrophic Risks from AI #2: Malicious Use by Dan H 1y ago

•

Applied to Catastrophic Risks from AI #1: Introduction by Dan H 1y ago

•

Applied to Rishi to outline his vision for Britain to take the world lead in policing AI threats when he meets Joe Biden by Mati_Roy 1y ago

•

Applied to [FICTION] ECHOES OF ELYSIUM: An Ai's Journey From Takeoff To Freedom And Beyond by Super AGI 2y ago

•

Applied to The way AGI wins could look very stupid by Christopher King 2y ago

•

Applied to Will GPT-5 be able to self-improve? by Nathan Helm-Burger 2y ago

•

Applied to Green goo is plausible by anithite 2y ago

Jacob Pfau v1.4.0Apr 12th 2023 GMT (+6/-6) 1

See also ~~Thread~~Threat Models

Jacob Pfau v1.3.0Apr 12th 2023 GMT (+6/-51) 1

See also Thread ~~Models: https://www.lesswrong.com/tag/threat-models~~Models