✳flâneur — a map of the web's best reading
Research Areas in Methods for Post-training and Elicitation (The Alignment Project by UK AISI) — AI Alignment Forum
alignmentforum.org · 1,839 words · saved by 1 readers
Post-training and elicitation techniques allow us to refine model behaviour for specific safety properties, providing crucial tools for alignment.
x Research Areas in Methods for Post-training and Elicitation (The Alignment Project by UK AISI) — AI Alignment Forum The Alignment Project Research Agenda AI Frontpage 6 Research Areas in Methods for Post-training and Elicitation (The Alignment Project by UK AISI) by Jacob Pfau , Benjamin Hilton 1st Aug 2025 Linkpost for alignmentproject.aisi.gov.uk 7 min read 0 6 The Alignment Project is a global fund of over £15 million, dedicated to accelerating progress in AI control and alignment research. It is backed by an international coalition of governments, industry, venture capital and philanthro
Explore this link on the map →saved by
related reading
- Research Areas in Evaluation and Guarantees in Reinforcement Learning (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- Research Areas in AI Control (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- Research Areas in Benchmark Design and Evaluation (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- Recent Redwood Research project proposals — AI Alignment Forumalignmentforum.org
- Research Areas in Interpretability (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- 7+ tractable directions in AI control — AI Alignment Forumalignmentforum.org
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Natural-emergent-misalignment-from-reward-hacking-paper.pdfassets.anthropic.com
- Should We Train Against (CoT) Monitors? — LessWronglesswrong.com
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- [2604.22082] Removing Sandbagging in LLMs by Training with Weak Supervisionarxiv.org