Coby Kassner
15 followers · 14 following · 311 views
on the atlas · 74
- Infinite Ethics3 savers
- philpapers.org/archive/EVAPOI.pdf1 savers
- Lie detection is best when it's cheap to cooperate — LessWrong1 savers
- Anthropic update on independent evaluators \ Anthropic2 savers
- The upcoming GPT-3 moment for RL | Mechanize Inc.8 savers
- How to fully automate software engineering | Mechanize Inc.5 savers
- Neural Networks Are Already Clean55 savers
- By default, Chinese AI falls very behind — LessWrong3 savers
- Becoming a magician – Autotranslucence44 savers
- Three AI Safety Related Ideas — LessWrong1 savers
- Two Neglected Problems in Human-AI Safety — LessWrong1 savers
- Plan R: AI Safety by ASICs — LessWrong5 savers
- We need a better theory of polarization, because it's failing to predict the AI debate — LessWrong1 savers
- How to shape policy from outside government4 savers
- An opinionated primer on Causal Decision Theory (CDT) and Evidential Decision Theory (EDT) — LessWrong1 savers
- Swarm Scaling — LessWrong2 savers
- Nate Soares' Life Advice - LessWrong5 savers
- How to have executive function – scribbles in the margins8 savers
- on doing Real work - by jessica dai7 savers
- [2607.24653] Kimi K3: Open Frontier Intelligence1 savers
- Rest in motion24 savers
- Data Bottlenecks Won't Stop an Intelligence Explosion2 savers
- Dario Amodei — We Must Pace the Frontier37 savers
- Defining alignment research — LessWrong2 savers
- The ML ontology and the alignment ontology — LessWrong1 savers
- Post 47: How I Formed My Own Views About AI Safety — Neel Nanda4 savers
- Dr. R. W. Hamming's Advice on Research14 savers
- How To Be Successful96 savers
- Research acceleration: The view inside OpenAI | OpenAI15 savers
- Superintelligent surveillance to prevent galactic anarchy3 savers
- Risk-Averse AIs4 savers
- Salad days — LessWrong6 savers
- The Dynamics of Intelligence Explosions — LessWrong1 savers
- Should We Lock in Post-AGI Agreements Under Uncertainty?1 savers
- Obvious advice11 savers
- What is the likelihood that civilizational collapse would directly lead to human extinction (within decades)? — EA Forum1 savers
- The Four Pillars: A Hypothesis for Countering Catastrophic Biological Risk3 savers
- How I think about catastrophic biological risk (part I): risk breakdown by type of response3 savers
- 21 Facts About Throwing Good Parties12 savers
- Letter Four – The Rainer Maria Rilke Archive1 savers
- Productivity: Working towards a summary of what we know3 savers
- Will reward-seekers respond to distant incentives? — LessWrong1 savers
- Privacy-Preserving AI Audit Tools — OpenMined2 savers
- Notes on "Managing to Change the World" — EA Forum3 savers
- Fitness-Seekers: Generalizing the Reward-Seeking Threat Model — LessWrong2 savers
- Many arguments for AI x-risk are wrong — AI Alignment Forum2 savers
- Reward is not the optimization target — LessWrong9 savers
- Some Ways I Think About Evaluating Grant Applications — LessWrong1 savers
- Strong Evidence is Common — LessWrong1 savers
- Be less scared of overconfidence | benkuhn.net16 savers
- My weekly review habit | benkuhn.net18 savers
- Impact, agency, and taste | benkuhn.net32 savers
- Do Things that Don't Scale13 savers
- How I select alignment research projects — LessWrong1 savers
- Learning By Writing43 savers
- The Moat of Low Status - by Sasha Chapin5 savers
- How to be More Agentic - by Cate Hall - Useful Fictions25 savers
- Be impatient | benkuhn.net24 savers
- Don't Build Mindreading — LessWrong7 savers
- Why do models task game? — LessWrong2 savers
- models may behave differently in graded episodes (a tirade) — LessWrong10 savers
- philpapers.org/archive/GOLLFC-2.pdf2 savers
- Stickiness in AI Behavioral Design1 savers
- What Should Go In A Model Spec?1 savers
- AI-Enabled Coups: How a Small Group Could Use AI to Seize Power13 savers
- What makes a strategy great2 savers
- Strategy as Problem-Solving > US Army War College - Publications > Display2 savers
- The impact merge - Joe Carlsmith2 savers
- A playbook for field strategy - by Dewi Erwan5 savers
- Good Strategy/Bad Strategy | Summary & Notes - Will Patrick1 savers
- The AI Industrial Explosion — Part 1: Maximum growth rates with current production methods4 savers
- Three Types of Intelligence Explosion9 savers
- Persistent Path-Dependence: Why Our Actions Matter Long-Term4 savers
- Curius / Bookmarks for the extremely curious190 savers