✳flâneur — a map of the web's best reading
Kaustubh Kislay
21 followers · 18 following · 230276 views
Open this reading profile →
on the atlas — 42
- Status Is The Game Of The Losers' Bracket — LessWrong2 savers
- Efficient tradeoffs and the safety-usefulness tradeoff model — LessWrong3 savers
- Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models1 savers
- how to write an essay | scribbles in the margins2 savers
- Your Left Brain Doesn't Trade With Your Right — LessWrong1 savers
- An Apple-Picking Model of AI R&D | Tom Cunningham – Tom Cunningham7 savers
- How to Actually Spend Billions on AI Safety - by Sophie Kim1 savers
- Natural Language Autoencoders \ Anthropic9 savers
- Risk from fitness-seeking AIs: mechanisms and mitigations1 savers
- Steering Might Stop Working Soon — LessWrong2 savers
- From personas to intentions: towards a science of motivations for AI models — LessWrong2 savers
- Fail safe(r) at alignment by channeling reward-hacking into a "spillway" motivation2 savers
- Not All Compute is Created Equal1 savers
- An extremely non-comprehensive list of how to increase your surface area for luck and magic (and instantly sprinkle fairy dust on your life)1 savers
- Do Thing, Do One Thing45 savers
- Hidden Role Games as a Trusted Model Eval - James Lucassen's Blog1 savers
- How to walk through walls - by Henrik Karlsson1 savers
- Model organisms researchers should check whether high LRs defeat their model organisms — LessWrong1 savers
- My six stages of learning to be a socially normal person4 savers
- What 3,654 Job Postings Tell Us About Talent Needs in AI Safety — EA Forum1 savers
- Changing the world for the worse — LessWrong1 savers
- Did Claude 3 Opus align itself via gradient hacking? — LessWrong16 savers
- How I've run major projects | benkuhn.net50 savers
- escaping flatland: career advice for CS undergrads41 savers
- Good conversations have lots of doorknobs31 savers
- When AI builds itself \ Anthropic30 savers
- The Persona Selection Model: Why AI Assistants might Behave like Humans28 savers
- How to win a best paper award (or, an opinionated take on how to do important research)24 savers
- A woefully incomplete guide to technical upskilling12 savers
- Inkling: Our Open-Weights Model - Thinking Machines Lab11 savers
- The behavioral selection model for predicting AI motivations — LessWrong10 savers
- 21 Facts About Throwing Good Parties8 savers
- There should be ‘general managers’ for more of the world’s important problems6 savers
- Security incident disclosure — July 20265 savers
- The 2026 Global Intelligence Crisis - Citadel Securities5 savers
- Strategic Taste5 savers
- A basic systems architecture for AI agents that do autonomous research — LessWrong4 savers
- A playbook for field strategy - by Dewi Erwan4 savers
- Bad Problems Don't Stop Being Bad Because Somebody's Wrong About Fault Analysis — LessWrong3 savers
- secret-loyalties-whitepaper.pdf3 savers
- Why I don't persuade people to do AI safety3 savers
- Not a Paper: "Frontier Lab CEOs are Capable of In-Context Scheming" — LessWrong2 savers