Arya Pasumarthi

on the atlas — 28

• Curius / Onboarding2507 savers
• Making Normal Conversations Better - by Sasha Chapin12 savers
• The behavioral selection model for predicting AI motivations — LessWrong10 savers
• Highly Opinionated Advice on How to Write ML Papers — AI Alignment Forum8 savers
• Off Target | CNAS7 savers
• llm assistant personas seem increasingly incoherent (some subjective observations) — LessWrong7 savers
• [2604.22082] Removing Sandbagging in LLMs by Training with Weak Supervision5 savers
• 'How to be a Human' Starter Pack - by Lydia Nottingham5 savers
• Maybe I was too harsh on deep learning theory (three days ago) — LessWrong5 savers
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviors4 savers
• The Hitchhiker's Guide to Actionable Interpretability4 savers
• [2601.21571] Shaping capabilities with token-level data filtering4 savers
• Don’t Outsource Your Thinking4 savers
• Plans A, B, C, and D for misalignment risk4 savers
• Should We Train Against (CoT) Monitors? — LessWrong3 savers
• [2603.02202] Frontier Models Can Take Actions at Low Probabilities3 savers
• Beliefs are Chosen to Serve Goals — LessWrong3 savers
• [2404.09932] Foundational Challenges in Assuring Alignment and Safety of Large Language Models2 savers
• Steering Might Stop Working Soon — LessWrong2 savers
• [2308.12108] The Local Learning Coefficient: A Singularity-Aware Complexity Measure2 savers
• Single Token Geometry: DeepSeek V4 and Manifold Tearing2 savers
• [2512.15584] A Decision-Theoretic Approach for Managing Misalignment2 savers
• [1507.01986] Toward Idealized Decision Theory2 savers
• What's so hard about continuous learning?2 savers
• Fail safe(r) at alignment by channeling reward-hacking into a "spillway" motivation2 savers
• Growth and Form in a Toy Model of Superposition — LessWrong2 savers
• Shtetl-Optimized » Blog Archive » Guess I’m A Rationalist Now2 savers
• From personas to intentions: towards a science of motivations for AI models — LessWrong2 savers