Working Memory Expansion - 惯性聚合

推荐订阅源

博客园 - 司徒正美

Darknet – Hacking Tools, Hacker News & Cyber Security

MIT News - Artificial intelligence

Microsoft Azure Blog

Microsoft Research Blog - Microsoft Research

阮一峰的网络日志

Help Net Security

Google Developers Blog

Stack Overflow Blog

人人都是产品经理

让小产品的独立变现更简单 - ezindie.com

博客园 - 【当耐特】

钛媒体：引领未来商业与生活新知

Recent Announcements

SegmentFault 最新的问题

大猫的无限游戏

博客园 - Franky

The Blog of Author Tim Ferriss

罗磊的独立博客

宝玉的分享

奇客Solidot–传递最新科技情报

DataBreaches.Net

Schneier on Security

Palo Alto Networks Blog

Hugging Face - Blog

CTFtime.org: upcoming CTF events

Kaspersky official blog

Privacy & Cybersecurity Law Blog

博客园_首页

Threat Research - Cisco Blogs

有赞技术团队

Threat Intelligence Blog | Flashpoint

Recorded Future

Hackread – Cybersecurity News, Data Breaches, AI and More

Check Point Blog

Proofpoint News Feed

LessWrong

Atomically precise mechanosynthesis of carbon structures on hydrogenated Si(100) by inverted-mode STM Constitutional AI Alignment LLMs Through the Eyes of Vinge Biologically Plausible SGD Is Hard Eval Cooperativeness May Be a Scalable Mitigation for Eval Gaming no, Magnifica Humanitas is not AI-written Albuquerque ACX Meetup Full automation of AI R&D probably yields a large speed up even without a software-only singularity Not Prosthetics BCI Cognition Enhancement is Possible The ballad of TIGIT Leveraging Introspection for Alignment Announcing Geodesic Research AI as a Social Technology, by Henry Farell More capable AI, less money raised Quantitative AI risk assessment: a starting point [paper] Training on Documents About Monitoring Leads to CoT Obfuscation No frontier model has acceptable levels of compliance with the EU AI Act and privacy legislation. Thinking outside the box? LLM analysis of simplified cooperative poker Standard deviations from just two values Simplifying Alignment by Expanding Scope You Can't Tell a Conscience From a Leash by Watching Should we train LLMs to be human? Are Mythos' Cyber Capabilities Overstated? - Yes and No Steering Directions Are Explanations, Not Handles Contra Wentworth on Physical Attractiveness for Men Finding the Mole: Bayesianism is Hard Training Language Models for Controlled Stochasticity Practical Learnings from Synthetic Document Finetuning Claude, Author of the Humanitas When does debate help a weak judge? Evidence from code and logic ACX Atlanta June 2026 Meetup — LessWrong RTMH: Pope Leo’s Magnifica Humanitas on AI — LessWrong The Fatal AGI Hardware Gap — LessWrong Many portions of Magnifica Humanitas appear to be AI-written — LessWrong Brain transfers might be the easiest path to life extension Some Thoughts on Bengio's Scientist AI Brackets Are a Bad Way to Regulate — LessWrong Donating 80% While It Still Counts Notes on Fourier Analysis Improving Petri scheming audits with environment blueprints Pope Leo’s First AI Encyclical – Summary and Commentary — LessWrong Cognitive Security as an AI Safety Cause Area — 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

Working Memory Expansion

Elliot Calle · 2026-05-28 · 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。