This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
AI
•
Applied to
Agentic GPT simulations: a risk and an opportunity
by
TagWrong
4h
ago
•
Applied to
Emergent Analogical Reasoning in Large Language Models
by
Roman Leventov
5h
ago
•
Applied to
AI Fables
by
Ruben Bloom
6h
ago
•
Applied to
[Linkpost] GatesNotes: The Age of AI has begun
by
Ruben Bloom
6h
ago
•
Applied to
Truth and Advantage: Response to a draft of "AI safety seems hard to measure"
by
TagWrong
7h
ago
•
Applied to
2023 Dallas ACX Schelling Meetup
by
TagWrong
8h
ago
•
Applied to
A Proposed Approach for AI Safety Movement Building: Projects, Professions, Skills, and Ideas for the Future [long post][bounty for feedback]
by
TagWrong
9h
ago
•
Applied to
Key Questions for Digital Minds
by
Jacy Reese Anthis
10h
ago
•
Applied to
God vs AI scientifically
by
Donatas Lučiūnas
12h
ago
•
Applied to
A method for empirical back-testing of AI's ability to self-improve
by
TagWrong
14h
ago
•
Applied to
the QACI alignment plan: table of contents
by
Tamsin Leake
14h
ago
•
Applied to
Adversarial (SEO) GPT training data?
by
TagWrong
16h
ago
•
Applied to
Why not constrain wetlabs instead of AI?
by
Lone Pine
17h
ago
•
Applied to
Stanford claims to have replicated ChatGPT for < $600
by
Ruben Bloom
17h
ago
•
Applied to
Some constructions for proof-based cooperation without Löb
by
TagWrong
19h
ago
•
Applied to
Clarifying mesa-optimization
by
Marius Hobbhahn
19h
ago
•
Applied to
AI #4: Introducing GPT-4
by
TagWrong
21h
ago
•
Applied to
Employer considering partnering with major AI labs. What to do?
by
GraduallyMoreAgitated
1d
ago