Cognitive Security as an AI Safety Cause Area — LessWrong - 惯性聚合

推荐订阅源

博客园 - 【当耐特】

博客园_首页

博客园 - 三生石上(FineUI控件)

Help Net Security

酷壳 – CoolShell

让小产品的独立变现更简单 - ezindie.com

阮一峰的网络日志

The GitHub Blog

DataBreaches.Net

美团技术团队

大猫的无限游戏

钛媒体：引领未来商业与生活新知

有赞技术团队

Stack Overflow Blog

Stack Overflow Blog

OSCHINA 社区最新新闻

Last Week in AI

博客园 - 司徒正美

Hackread – Cybersecurity News, Data Breaches, AI and More

The Blog of Author Tim Ferriss

WordPress大学

Hugging Face - Blog

博客园 - Franky

人人都是产品经理

博客园 - 聂微东

Google DeepMind News

奇客Solidot–传递最新科技情报

Visual Studio Blog

Microsoft Security Blog

LINUX DO - 最新话题

Know Your Adversary

Tor Project blog

SegmentFault 最新的问题

Future of Privacy Forum

The Hacker News

李成银的技术随笔

Proofpoint News Feed

True Tiger Recordings

LessWrong

Sentient Welfare Across Three Futures — LessWrong Linkpost: New Vatican Encyclical on AI Governance — LessWrong How AI Will Save Prediction Markets There should be a discussion about LW's policy to allow calls for violence Character-trained models can struggle to generalise — LessWrong Applications open for the Secure Program Synthesis Fellowship — LessWrong Announcing the Frontier Biodefense Fellowship (deadline 2 June) We Need Unhobbled Donors — LessWrong Taxing Small Cars To Improve MPG — LessWrong A (Slightly) Mechanistic Theory for Exponentially Increasing AI Time Horizons? Neurogastronomic Phenomenology for Advanced Beginners, Applied and Pure Heretical Pasta Veganism is Virtuous, not Obligatory — LessWrong Veganism is Virtuous but not Obligatory — LessWrong Low Expectancy is Not a Confidence Problem Basic principles for dressing better. Boltzmann brains, like Doomsday, require no explaining — LessWrong Probabilities are not the right concept — LessWrong Your Left Brain Doesn't Trade With Your Right — LessWrong The Fundamentals of Cogitism: Grounding Ethics in the Nature of Consciousness — LessWrong The Leaky AI Safety Pipeline — LessWrong Can Large Language Models Identify Novel Threats? Part 1: Mirror Life and the Classification Gap — LessWrong Capitalism is only the first of our problems — LessWrong A political movement will save us from extinction How should we update on AI-enabled coups post-Mythos? — LessWrong Out-of-Context Reasoning (OOCR) in LLMs: A Short Primer and Reading List Looking for backdoors in Jane Street LLMs PLA Daily Translation: Reflections on Warfare Brought by AGI — LessWrong Will we really put data centers in space? — LessWrong We made a map of the doom debate — LessWrong Which technical AI safety fields are going to be automated first? Gemini 3.5 Flash Looks Good For How Fast It Is — LessWrong The AI Industrial Explosion — Part 3: Going faster — LessWrong Strong Longtermism Is Simply Correct — LessWrong Notes on Collaborating with Claude Opus — LessWrong Proposal for "Timelines to what": DIAL distribution — LessWrong Insurance Premiums To The Moon AI is Not Normal Technology Counting Arguments in AI Safety — LessWrong You can opt out of allergies — LessWrong Moderator's Principle of Least Surprise Possible red is red Apr-May 2026 AI Security via Formal Methods — LessWrong An Introduction to Neo-Fatalism — LessWrong Loss of Oversight: How AI Systems May Become Harder to Audit, Monitor, and Investigate What am I, if not an AI? — LessWrong AI #169: New Knowledge Learned Chain-of-Thought Obfuscation Generalises to Unseen Tasks Numb mental state shifts — LessWrong Women should be able to open things — LessWrong Why are people so scared of causing fear? Document-tuning instills durable animal compassion in LLMs (and generalizes to humans) What About Us? The Whole Kitten-Cavoodle Why does off-model SFT degrade capabilities? — LessWrong If I Were Emperor of New AI Safety Researcher Training... — LessWrong theory uplift differentially benefits safety & is underleveraged Singular Learning Theory Comprehensive - 1 — LessWrong Sparse Efficiency vs. Superposition: The Interpretability Tradeoff — LessWrong The Case for Evaluating Model Behaviors Toward Interoperability of Minimal Programs — LessWrong Fundamental Uncertainty $2,000 Essay Contest — LessWrong Check out my technological uplifting, civilization-building, and science in a magic world fiction! Synthetic Persona Pretraining: Alignment from Token Zero — LessWrong Give my children minds — LessWrong Power-seeking agents will likely be developed — LessWrong Apply now to Human-Aligned AI Summer School 2026 — LessWrong From 8B to Frontier: How System Prompts Control Whether AI Agents Blackmail, Leak, and Kill — LessWrong If AI is normal technology, history is not reassuring. Pythagorean addition — LessWrong So you don't want everybody to die — LessWrong Temporal Proportional Representation Conclave 1492 Childhood And Education #19: Letting Kids Be Kids #2 — LessWrong Implications Of Predicting The Next Token Housing Roundup #15: The War Against Renters Leaving DCA to the North on Foot A Visual Guide to Natural Latents — LessWrong Humans are not automatically strategic — "inner work" edition Cyborg Uplift Studies We Need to Get Serious about Uplift Studies Brain Structure and IQ: How Myelin Elevates Intelligence Sealing Conditional Misalignment in Inoculation Prompting with Consistency Training Let's have more partial insiders. Roadmap through AI safety programs for early-career technical researchers Should Rationalists Looksmaxx? When Fluency Is Free AI emotions and aligned behavior Tracking Difficulty with Feature Portfolios Outsiders should focus on specs/constitutions Outsiders should focus on specs/constitutions (among other things) Logical Share Splitting for Intuitionists Coordinal: A Postmortem. Noticing Confusion: A practice in staying curious Dating Roundup #12: Sex and Violence Negation Neglect: When models fail to learn negations in training So are you some kind of communist? Thoughts on interviewing candidates for AI safety fellowships PauseAI Munich Local Group Kickoff Classifier Context Rot: Monitor Performance Degrades with Context Length

Cognitive Security as an AI Safety Cause Area — LessWrong

jsteinhardt · 2026-05-26 · via LessWrong

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。