Difference between revisions of "AI safety"
KevinYager (talk | contribs) |
KevinYager (talk | contribs) (→Key Concepts) |
||
| Line 7: | Line 7: | ||
* [https://www.alignmentforum.org/w/mesa-optimization Mesa-optimization] | * [https://www.alignmentforum.org/w/mesa-optimization Mesa-optimization] | ||
* [https://www.lesswrong.com/posts/N6vZEnCn6A95Xn39p/are-we-in-an-ai-overhang Overhang] | * [https://www.lesswrong.com/posts/N6vZEnCn6A95Xn39p/are-we-in-an-ai-overhang Overhang] | ||
| + | * [https://www.alignmentforum.org/posts/pdaGN6pQyQarFHXF4/reward-is-not-the-optimization-target Reward is not the optimization target] (Alex Turner) | ||
==Medium-term Risks== | ==Medium-term Risks== | ||
Revision as of 13:54, 14 February 2025
Contents
Description of Safety Concerns
Key Concepts
- Instrumental Convergence
- Orthogonality Thesis
- Inner/outer alignment
- Mesa-optimization
- Overhang
- Reward is not the optimization target (Alex Turner)
Medium-term Risks
- 2023-04: A.I. Dilemma – Tristan Harris and Aza Raskin” (video) (.website-files.com/5f0e1294f002b1bb26e1f304/64224a9051a6637c1b60162a_65-your-undivided-attention-The-AI-Dilemma-transcript.pdf podcast transcript): raises concern about human ability to handle these transformations
- 2023-04: Daniel Schmachtenberger and Liv Boeree (video): AI could accelerate perverse social dynamics
- 2023-10: Sociotechnical Safety Evaluation of Generative AI Systems (Google DeepMind)
Long-term (x-risk)
- List AGI Ruin: A List of Lethalities (Eliezer Yudkowsky)
Learning Resources
Research
- 2022-12: Discovering Latent Knowledge in Language Models Without Supervision
- 2023-02: Pretraining Language Models with Human Preferences
- 2023-04: Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
- 2023-05: Model evaluation for extreme risks (DeepMind)
- 2023-05: Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
- 2023-06: Preference Ranking Optimization for Human Alignment
- 2023-08: Self-Alignment with Instruction Backtranslation
- 2023-11: Debate Helps Supervise Unreliable Experts
