✳flâneur — a map of the web's best reading
Arjun Khandelwal
20 followers · 23 following · 1224 views
Open this reading profile →
on the atlas — 78
- Pyramid Replacement - The Intelligence Curse5 savers
- The future of alignment if LLMs are a bubble — LessWrong1 savers
- Thoughts on the conservative assumptions in AI control2 savers
- How can we solve diffuse threats like research sabotage with AI control?1 savers
- Win/continue/lose scenarios and execute/replace/audit protocols1 savers
- Test your interpretability techniques by de-censoring Chinese models — LessWrong5 savers
- How To Become A Mechanistic Interpretability Researcher — AI Alignment Forum5 savers
- Does Reality Drive Straight Lines On Graphs, Or Do Straight Lines On Graphs Drive Reality? | Slate Star Codex3 savers
- Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Data6 savers
- Mode collapse2 savers
- Conditioning, Prompts, and Fine-Tuning — LessWrong1 savers
- Types of financial risks (video) | Insurance | Khan Academy1 savers
- Charitable giving (video) | Financial goals | Khan Academy1 savers
- Choosing a credit card: credit card types (article) | Khan Academy1 savers
- How do I raise my credit score? (article) | Khan Academy1 savers
- What can change your credit score? (video) | Khan Academy1 savers
- What is a budget? (article) | Budgeting | Khan Academy1 savers
- "Greg Brockman works 60 to 100 hours per week, and spends around 80% of the time... | Hacker News1 savers
- On Owning Galaxies — LessWrong1 savers
- Turning 20 in the probable pre-apocalypse — LessWrong8 savers
- How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day1 savers
- The inaugural Redwood Research podcast - by Buck Shlegeris2 savers
- taboo1 savers
- 'How to be a Human' Starter Pack - by Lydia Nottingham5 savers
- Many can write faster asm than the compiler, yet don't. Why? — LessWrong1 savers
- My template for a quarterly review + plan1 savers
- Alignment remains a hard, unsolved problem — LessWrong14 savers
- Researching from the Heart 💗 - by mrinank1 savers
- Curated AI Career Advice - by Saheb Gulati2 savers
- Curius / Onboarding2507 savers
- How To Be Successful90 savers
- You and Your Research76 savers
- What I Wish Someone Had Told Me - Sam Altman51 savers
- AI 202749 savers
- You don’t need to work on hard problems47 savers
- LessWrong34 savers
- https://cs.stanford.edu/~jsteinhardt/ResearchasaStochasticDecisionProcess.html26 savers
- Do I Need to Go to University? -- colah's blog25 savers
- Visual Information Theory -- colah's blog23 savers
- Advice on Upskilling - Justin Skycak22 savers
- Research Taste Exercises [rough note] -- colah's blog21 savers
- Lil'Log21 savers
- Galaxy brain resistance18 savers
- Should You Reverse Any Advice You Hear? | Slate Star Codex18 savers
- Building the heap: racking 30 petabytes of hard drives for pretraining | blog17 savers
- How I became a machine learning practitioner16 savers
- AGI Ruin: A List of Lethalities - LessWrong15 savers
- My path to OpenAI15 savers
- It Is Your Responsibility to Follow Up - Alexey Guzey10 savers
- The behavioral selection model for predicting AI motivations — LessWrong10 savers
- Defining the Intelligence Curse - The Intelligence Curse10 savers
- 2025 year in review | Kevin Liu10 savers
- The Law of Leaky Abstractions – Joel on Software10 savers
- Shipping at Inference-Speed | Peter Steinberger9 savers
- Thinking Machines Lab9 savers
- Gears in understanding - LessWrong9 savers
- The making of OpenAI - Greg Brockman8 savers
- Spaced Repetition Systems Have Gotten Way Better | Domenic Denicola8 savers
- The Roots of Progress7 savers
- Andrej Karpathy — AGI is still a decade away7 savers
- Where I agree and disagree with Eliezer — LessWrong6 savers
- On love & relationships | Evan Conrad6 savers
- reactive agency - by Claire Wang - cold brew blog6 savers
- Plans A, B, C, and D for misalignment risk — LessWrong5 savers
- Workshop Labs PBC5 savers
- X explains Z% of the variance in Y — LessWrong5 savers
- How confessions can keep language models honest | OpenAI5 savers
- corner.inc5 savers
- Kalman filter5 savers
- In defense of blub studies | benkuhn.net4 savers
- A basic systems architecture for AI agents that do autonomous research — LessWrong4 savers
- The Case Against AI Control Research — LessWrong4 savers
- Matthew effect4 savers
- AI Futures Model: Dec 2025 Update3 savers
- Applause Lights — LessWrong2 savers
- Thoughts on the Singularity Institute (SI) — LessWrong2 savers
- Life after work | Mechanize Inc.2 savers
- A list of other catastrophes that are probably fake2 savers