Linus Tang
2 followers · 4 following · 55 views
on the atlas — 37
- Greater good arguments in AI safety — LessWrong1 savers
- Review of the "Misalignment in high-stakes settings" section in Anthropic's Risk Report (August 2026)1 savers
- Against Against Handover - by Scott Alexander1 savers
- An Opinionated Guide to Privacy Despite Authoritarianism1 savers
- Misaligned! - by Zvi Mowshowitz1 savers
- The Talker Does Not Control The Doer (in Current AIs) — LessWrong3 savers
- OpenAI Fires Three Safety Researchers - by Zvi Mowshowitz1 savers
- Anthropic Does Not Understand Why Its Draft Bill Was Unacceptable and Troubling1 savers
- Nathan Calvin on Anthropic Bill1 savers
- Update-Aware Reasoning in GLM-5.3: Training & Alignment Faking1 savers
- Preparing for a Cybersecurity Catastrophe — LessWrong1 savers
- Quick notes from teaching technical profiles how to talk in public — LessWrong2 savers
- The world's best gradual disempowerment model organism: Frontier AI labs — LessWrong1 savers
- Neural networks are not already clean — LessWrong5 savers
- Leaked Anthropic Draft AI Regulatory Bill Is Unacceptable and Troubling1 savers
- Surfacing Pathological Behaviors in Language Models | Transluce AI5 savers
- Microsoft Word - LockhartsLament.doc6 savers
- A civilization ran by amateurs — LessWrong1 savers
- …And I Show You How Deep The Rabbit Hole Goes | Slate Star Codex4 savers
- Universal Love, Said The Cactus Person16 savers
- In Defense of Punch Bug - by Duncan Sabien - Homo Sabiens1 savers
- Truth or Dare - by Duncan Sabien - Homo Sabiens1 savers
- What's the date? — LessWrong6 savers
- Trust develops gradually via making bids and setting boundaries — LessWrong3 savers
- MacGregor The Bridge Builder - by Scott Alexander1 savers
- The Foothills Of Bay Area House Party - by Scott Alexander4 savers
- My Antichrist Lecture - by Scott Alexander4 savers
- See the dark world4 savers
- Have no excuses6 savers
- Detach the grim-o-meter3 savers
- Early rogue AI agent activity and attempts to hack found on urlquery.net | Transluce AI4 savers
- The Specter Of Neuralese - by Scott Alexander1 savers
- AI Safety Is Not A Corporate Plot - by Scott Alexander2 savers
- Being John Rawls - by Scott Alexander - Astral Codex Ten5 savers
- Only Law Can Prevent Extinction — LessWrong3 savers
- How Go Players Disempower Themselves to AI — LessWrong10 savers
- Capabilities research expands the safety-usefulness Pareto frontier too — LessWrong1 savers