Does SGD Produce Deceptive Alignment? - LessWrong
Deceptive alignment was first introduced in Risks from Learned Optimization, which contained initial versions of the arguments discussed here. Additional arguments were discovered in this episode of…
x Does SGD Produce Deceptive Alignment? — LessWrong Deceptive Alignment Inner Alignment Machine Learning (ML) Mesa-Optimization Distillation & Pedagogy AI Frontpage 96 Does SGD Produce Deceptive Alignment? by Mark Xu 6th Nov 2020 AI Alignment Forum 19 min read 9 96 Ω 43 Deceptive alignment was first introduced in Risks from Learned Optimization , which contained initial versions of the arguments discussed here. Additional arguments were discovered in this episode of the AI Alignment Podcast and in conversation with Evan Hubinger. Very little of this content is original. My contributions consis
related reading
- Deep Deceptiveness — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Alignment Faking Mitigationsalignment.anthropic.com
- How likely is deceptive alignment? — AI Alignment Forumalignmentforum.org
- New report: “Scheming AIs: Will AIs fake alignment during training in order to get power?”joecarlsmith.com
- Deceptive Alignment — AI Alignment Forumalignmentforum.org
- Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research — AI Alignment Forumalignmentforum.org
- Self-Other Overlap: A Neglected Approach to AI Alignment — LessWronglesswrong.com
- Should We Train Against (CoT) Monitors? — LessWronglesswrong.com
- Risks from Learned Optimization: Introduction — LessWronglesswrong.com
- Why AI alignment could be hard with modern deep learningcold-takes.com
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com