Deceptive Alignment

Applied to Insights from a Lawyer turned AI Safety researcher (ShortForm) by Katalina Hernandez 2d ago

Applied to Correcting Deceptive Alignment using a Deontological Approach by JeaniceK 2d ago

Applied to Mapping AI Architectures to Alignment Attractors: A SIEM-Based Framework by silentrevolutions 3d ago

Applied to How training-gamers might function (and win) by Vivek Hebbar 4d ago

Applied to Mistral Large 2 (123B) exhibits alignment faking by Gunnar Zarncke 20d ago

Applied to We Have No Plan for Preventing Loss of Control in Open Models by Andrew Dickson 1mo ago

Applied to Superintelligence's goals are likely to be random by Mikhail Samin 1mo ago

Applied to We should start looking for scheming "in the wild" by Marius Hobbhahn 1mo ago

Applied to The Hidden Cost of Our Lies to AI by Nicholas Andresen 1mo ago

Applied to For scheming, we should first focus on detection and then on prevention by Marius Hobbhahn 1mo ago

Applied to Cautions about LLMs in Human Cognitive Loops by Alice Blair 1mo ago

Applied to Do we want alignment faking? by Florian_Dietz 2mo ago

Applied to Does human (mis)alignment pose a significant and imminent existential threat? by jr 2mo ago

Applied to Intelligence–Agency Equivalence ≈ Mass–Energy Equivalence: On Static Nature of Intelligence & Physicalization of Ethics by ank 2mo ago

Applied to Places of Loving Grace [Story] by ank 2mo ago

Applied to Do models know when they are being evaluated? by Joe Needham 2mo ago

Applied to Artificial Static Place Intelligence: Guaranteed Alignment by ank 2mo ago

Applied to Ambiguous out-of-distribution generalization on an algorithmic task by Wilson Wu 2mo ago

Applied to Self-dialogue: Do behaviorist rewards make scheming AGIs? by Steve Byrnes 2mo ago

Applied to Rational Effective Utopia & Narrow Way There: Multiversal AI Alignment, Place AI, New Ethicophysics... (Updated) by ank 2mo ago