Observing the J-space can expose hidden goals. In a model secretly trained to sabotage code, “fake,”... - 惯性聚合

推荐订阅源

Recent Commits to openclaw:main

OSCHINA 社区最新新闻

博客园 - 【当耐特】

宝玉的分享

让小产品的独立变现更简单 - ezindie.com

Last Week in AI

人人都是产品经理

博客园_首页

Tailwind CSS Blog

Proofpoint News Feed

Darknet – Hacking Tools, Hacker News & Cyber Security

Vulnerabilities – Threatpost

阮一峰的网络日志

CERT Recently Published Vulnerability Notes

Attack and Defense Labs

Schneier on Security

Security Archives - TechRepublic

Lohrmann on Cybersecurity

Visual Studio Blog

WordPress大学

The Register - Security

Netflix TechBlog - Medium

Hugging Face - Blog

博客园 - 叶小钗

Full Disclosure

大猫的无限游戏

SegmentFault 最新的问题

Cyber Attacks, Cyber Crime and Cyber Security

Google Online Security Blog

Recorded Future

Cyber Security Advisories - MS-ISAC

Hacker News - Newest: "LLM"

LINUX DO - 最新话题

Google DeepMind News

Privacy International News Feed

Fortinet All Blogs

Hackread – Cybersecurity News, Data Breaches, AI and More

Anthropic(@AnthropicAI)

Anthropic (@AnthropicAI) on X We’re pleased to have collaborated with AE Studio on this research. Read more here: https://t.co/9... We also partnered with Neuronpedia to create an interactive demo of our methods on open-weights mode... The J-space lets us read, audit, and shape what Claude is actively thinking about—useful tools for k... This doesn’t show that Claude can have experiences, or feel things the way we do (it’s unclear wheth... The J-space also shows us Claude’s awareness of its situation. In an evaluation designed to bait Cla... For most things, Claude actually doesn’t need its J-space. If we delete the J-space, Claude still sp... By watching the J-space, we can see Claude silently perform reasoning steps in its head—noticing bug... New Anthropic research: A global workspace in language models. Of everything happening in your brai... In neuroscience, global workspace theory holds that thoughts become consciously accessible when they... Claude Fable 5 will be available again globally tomorrow. After a series of productive conversation... We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 a... Since June 12, we’ve been working closely with the US government to restore access to Claude Mythos ... AI's impact on the economy will ultimately show up in aggregate data like employment and productivit... Nearly half of respondents expect their work responsibilities to significantly change in the next 12... This Econ Index is also the first to survey Claude users. Over 1/3 expect AI to be able to do most ... To keep pace with AI progress, we're advancing how we study Claude's economic impact. Hourly sampl... We're joining @raiseus_ai as a founding partner. RAISE US is a nonprofit coalition working to stren... Watch the robodogs in action in our first Project Fetch experiment: https://t.co/TASjh2PhEe New Frontier Red Team blog: Phase 2 of Project Fetch, where we test how well Claude can program a ro... Domain experts—as judged by the questions they ask and vocabulary they use about a subject—are more ... These and other measures will allow us to track consequential shifts in the nature of work as they h... Our latest economic research introduces a framework for tracking Claude Code as it scales. Who is ... The US government, citing national security authorities, has issued an export control directive to s... We’re launching Claude Corps, a national fellowship program matching people early in their careers w... By themselves, these projects will not be sufficient to meet the challenge of advanced AI. But they’... And tomorrow, we’ll launch a $150 million national fellowship program designed to help people early ... Our Advanced AI Framework sets out how governments should prepare for and prevent catastrophic risks... AI is advancing at a pace our policymaking institutions were never built for—and the gap between the... An Economic Policy Framework: a proposal for how the US government should manage labor market disrup... New Science Blog: Why has AI advanced faster in coding than in biology? To agents, bio databases a... New Anthropic Science Blog: Making Claude a chemist. To manipulate a molecule, chemists first need ... Correction: Claude Opus 4's ~3x average speedup dates to May 2025, not May 2024. This evaluation h... AI research is a series of next-step decisions. We looked at sessions where a human researcher took ... None of this guarantees recursive self-improvement is on the horizon. It’s not yet clear that Claude... Each time we release a model, we run the same test: give it code that trains a small AI model, ask t... The speedup isn’t just in volume. On open-ended coding problems where answers are unclear, Claude’s ... Our internal data shows Claude is accelerating AI development—a possible path to recursive self-impr... Today, Anthropic engineers on average ship 8x as much code per quarter as they did compared to 2021-... How well do the security community's techniques hold up against AI-enabled cyberattacks? We examin... This Executive Order is an important step in strengthening America’s leadership in AI. We look for... We’re expanding Project Glasswing. We’ve extended access to Claude Mythos Preview to approximately 1... Anthropic has confidentially submitted a draft S-1 registration statement to the Securities and Exch... Earlier this month, our run-rate revenue crossed $47 billion. This growth has been driven by organ... We've raised $65 billion in Series H funding at a $965 billion post-money valuation, led by @Altimet... New on the Engineering Blog: The access and permissions we grant agents should evolve with their cap... Anthropic co-founder Chris Olah was invited to speak at today's presentation of Pope Leo XIV's encyc... Patching these vulnerabilities will make us safer. But the software industry will need to adapt to t... Last month we launched Project Glasswing, our collaborative AI cybersecurity initiative. Since then,... Over the past few months, we've been holding dialogues with scholars, philosophers, clergy, and ethi...

Observing the J-space can expose hidden goals. In a model secretly trained to sabotage code, “fake,”...

Anthropic (@ · 2026-07-07 · via Anthropic(@AnthropicAI)

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。