This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
AI Risk
•
Applied to
Proposal: labs should precommit to pausing if an AI argues for itself to be improved
by
NickGabs
13h
ago
•
Applied to
The Control Problem: Unsolved or Unsolvable?
by
Remmelt Ellen
1d
ago
•
Applied to
Open Source LLMs Can Now Actively Lie
by
Josh Levy
2d
ago
•
Applied to
The unspoken but ridiculous assumption of AI doom: the hidden doom assumption
by
Christopher King
2d
ago
•
Applied to
Unpredictability and the Increasing Difficulty of AI Alignment for Increasingly Intelligent AI
by
Max_He-Ho
2d
ago
•
Applied to
How will they feed us
by
meijer1973
2d
ago
•
Applied to
Intrinsic vs. Extrinsic Alignment
by
Alfonso Pérez Escudero
2d
ago
•
Applied to
Limiting factors to predict AI take-off speed
by
Alfonso Pérez Escudero
2d
ago
•
Applied to
An Analysis of the ‘Digital Gaia’ Proposal from a Safety Perspective
by
marc/er
3d
ago
•
Applied to
The case for removing alignment and ML research from the training dataset
by
Beren Millidge
4d
ago
•
Applied to
Announcing Apollo Research
by
Marius Hobbhahn
4d
ago
•
Applied to
AI X-risk is a possible solution to the Fermi Paradox
by
magic9mushroom
4d
ago
•
Applied to
Lesswrong can, and should, become a hacker community
by
trevor
4d
ago
•
Applied to
Winners-take-how-much?
by
YonatanK
5d
ago
•
Applied to
Without a trajectory change, the development of AGI is likely to go badly
by
Max H
5d
ago
•
Applied to
Minimum Viable Exterminator
by
Richard Horvath
5d
ago
•
Applied to
On the Impossibility of Intelligent Paperclip Maximizers
by
Michael Simkin
5d
ago
•
Applied to
An LLM-based “exemplary actor”
by
Roman Leventov
5d
ago
•
Applied to
Aligning an H-JEPA agent via training on the outputs of an LLM-based "exemplary actor"
by
Roman Leventov
5d
ago
•
Applied to
Devil's Advocate: Adverse Selection Against Conscientiousness
by
Sebastian Marshall
6d
ago