AI ALIGNMENT FORUMTags
AF

AI Risk Concrete Stories

•

Applied to Brainstorming: Slow Takeoff by David Piepgrass 3mo ago

•

Applied to "Humanity vs. AGI" Will Never Look Like "Humanity vs. AGI" to Humanity by Thane Ruthenis 4mo ago

•

Applied to Challenge proposal: smallest possible self-hardening backdoor for RLHF by Christopher King 10mo ago

•

Applied to Catastrophic Risks from AI #6: Discussion and FAQ by Dan H 10mo ago

•

Applied to Catastrophic Risks from AI #5: Rogue AIs by Dan H 10mo ago

•

Applied to Catastrophic Risks from AI #4: Organizational Risks by Dan H 10mo ago

•

Applied to Catastrophic Risks from AI #3: AI Race by Dan H 10mo ago

•

Applied to Catastrophic Risks from AI #2: Malicious Use by Dan H 10mo ago

•

Applied to Catastrophic Risks from AI #1: Introduction by Dan H 10mo 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 10mo ago

•

Applied to [FICTION] ECHOES OF ELYSIUM: An Ai's Journey From Takeoff To Freedom And Beyond by Super AGI 1y ago

•

Applied to The way AGI wins could look very stupid by Christopher King 1y ago

•

Applied to Will GPT-5 be able to self-improve? by Nathan Helm-Burger 1y ago

•

Applied to Green goo is plausible by Richard Thiessen 1y ago

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

See also ~~Thread~~Threat Models

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

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

Jacob Pfau v1.2.0Apr 12th 2023 (+21/-23)

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

Jacob Pfau v1.1.0Apr 12th 2023 (+69)

See also [Thread Models](https://www.lesswrong.com/tag/threat-models)

•

Applied to AI x-risk, approximately ordered by embarrassment by Alex Lawsen 1y ago