Difference between revisions of "AI safety"
KevinYager (talk | contribs) (→Research) |
KevinYager (talk | contribs) (→Research) |
||
| Line 18: | Line 18: | ||
* 2023-05: [https://arxiv.org/abs/2305.03047 Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision] | * 2023-05: [https://arxiv.org/abs/2305.03047 Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision] | ||
* 2023-06: [https://arxiv.org/abs/2306.17492 Preference Ranking Optimization for Human Alignment] | * 2023-06: [https://arxiv.org/abs/2306.17492 Preference Ranking Optimization for Human Alignment] | ||
| + | * 2023-08: [https://arxiv.org/abs/2308.06259 Self-Alignment with Instruction Backtranslation] | ||
Revision as of 13:46, 14 February 2025
Contents
Description of Safety Concerns
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
Long-term (x-risk)
Learning Resources
Research
- 2022-12: Discovering Latent Knowledge in Language Models Without Supervision
- 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
