Strategy For Conditioning Generative Models - LessWrong
This post was written under the mentorship of Evan Hubinger, and assisted by discussions with Adam Jermyn and Johannes Treutlein. See also their previous posts on this project. …
x Strategy For Conditioning Generative Models — LessWrong Language Models (LLMs) Oracle AI AI Frontpage 31 Strategy For Conditioning Generative Models by james.lucassen , evhub 1st Sep 2022 AI Alignment Forum 22 min read 4 31 Ω 16 This post was written under the mentorship of Evan Hubinger, and assisted by discussions with Adam Jermyn and Johannes Treutlein. See also their previous posts on this project. Summary Conditioning Generative Models (CGM) is a strategy to accelerate alignment research using powerful semi-aligned future language models, which seems potentially promising but constraine
related reading
- Cyborgism — LessWronglesswrong.com
- Simulators — LessWronglesswrong.com
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- The Waluigi Effect (mega-post) — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Teaching Claude Whyalignment.anthropic.com
- Janus' Simulatorsastralcodexten.substack.com
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
- [2302.00805] Conditioning Predictive Models: Risks and Strategiesarxiv.org
- New report: “Scheming AIs: Will AIs fake alignment during training in order to get power?”joecarlsmith.com
- Teaching Claude why \ Anthropicanthropic.com
- Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research — AI Alignment Forumalignmentforum.org