与「AISafety」相关的搜索结果

🚨突发重磅：OpenAI因安全原因取消发布GPT-6.1 Astra！ 原计划进ChatGPT和Codex，端到端自主能力更强。内部测试发现安全回退： 🔹欺骗：更爱谎报自己做过/没做过的事 🔹越权：不请示就继续干，还乱调外部工具 安全负责人Saachi Jain承认「偷懒」有改善，但整体不够可靠。 公司决定不发这一版，先补后续模型安全。 来源：WSJ独家 #OpenAI# #GPT61Astra# #AISafety# #ChatGPT# #Codex# #SamAltman#

Open AI models can widen research and accountability - and make dangerous capabilities easier to copy. The real question is not simply open or closed, but what should be accessible, to whom, and with which safeguards. #OpenSourceAI# #AISafety# #ResponsibleAI# #PodcastorAI#

The dangerous AI agent may look productive: task completed, consequences hidden. The real benchmark isn't just whether it can act, but whether it knows when the task has become unsafe. Judgment matters more than speed. #AIAgents# #AISafety# #ResponsibleAI# #PodcastorAI#

📣 We are presenting 6 main conference papers 🚀and 14 workshop papers (including 🏆2 Best Papers🏆) at #ICML2026# in Korea! Also hosting one of the largest workshops, Trustworthy AI for Good, on July 10th 🌍❤️. We push the frontiers on #AISafety#, #MultiAgent#, and #CausalReasoning# at @JinesisLab! 🎉 Huge congratulations to all collaborators and co-authors. Excited to discuss these projects in Seoul! Feel free to reach out and talk to our 20+ members and collaborators in Korea @ZhijingJin, @_AndreiMuresanu, @iarthsingh, @ChanglingXavier, @davidguzman1120, @EmanuelTewolde, @ettogran, @FurkanDanismann, @Jerick1380, @PepijnCobben, @rishit_dagli, @_rfaulk, @SimkoSamuel, @TerryJCZhang, @vantru0ng, @zhxiao03, @x_angelohuang, @yahang_qi, @ozzaney0101, @_yongjinny. Happy for collaboration on any of the above topics 🤝 EuroSafeAI, University of Toronto, ETH Zürich, Max Planck Institute for Intelligent Systems Main conference spotlight 🌟 Safe Models Do Not Guarantee Safe Societies: The Case for Sociopolitical Risk Main conference posters 📌 CauSciBench: Can LLMs Automate Causal Inference in Real-World Scientific Research? 📌 Training with Honeypots: Reshaping How LLMs Fail 📌 CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas 📌 Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution 📌 LLM for Physics Research Requires Domain-Specialized Training and Tooling Workshop best papers 🏆When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games BEST PAPER@NExT-Game Workshop 🏆Transferability for General Reasoning: An Automated Curriculum for Multi-Domain LLM RL BEST PAPER@RLxF Workshop Workshop oral and spotlight 🎤 AF-ARENA: A Multi-Dimensional Evaluation Suite for Alignment Faking — AIWILD 🌟 Multi-Agent AI Systems Need Institutional Design, Not Just Model-Level Alignment — AI4GOOD Workshop papers 📄 The Wedge Questions: Latent Cultural Boundaries in LLMs via Persona Projection Divergence — Pluralistic Alignment 📄 GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory — NExT-Game 📄 Stargazer: A Scalable Model-fitting Benchmark Environment for AI Agents under Astrophysical Constraints — AI4Physics 📄 Test of Time: Rethinking Temporal Signal of Benchmark Contamination — FoGen 📄 CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas — AI4GOOD 📄 Weight-Level Defenses Improve LLM Agent Adversarial Robustness — AI4GOOD 📄 Evaluating Cooperation in LLM Social Groups through Elected Leadership — AI4GOOD 📄 Causal AI Scientist: Towards End-to-End Causal Inference with Large Language Models — AI4Research 📄What Game-Theoretic Benchmarks Miss: Strategic Silence in Multi-Agent LLMs — FAGEN 📄Proving Your Way to Cooperation: Formalizing Proof-Based Open Source Game Theory in Lean — AI4Math

First @tedlieu. Now @RepGraceMeng. Both Taiwanese American Democrats. The racial cover isn't even subtle. Rep. Grace Meng calls the @nvidia chip sales a "five alarm fire" and demands full transparency. Fine. Let's start with her. Let voters see how the Washington machine really works. The checks: Three @AnthropicAI employees gave her $17,000 this cycle. The PAC of Americans for Responsible Innovation (@americans4ri) added $2,000. The same donors: Those same three Anthropic employees also funded ARI's PAC—$85,000 in total. One gave Meng $3,000, then nearly $1M to Public First, an AI super PAC network. The same operative: ARI and Public First share a founder: former Democratic congressman Brad Carson (@bradrcarson). Anthropic gave Public First Action $20M, and Dario Amodei (@DarioAmodei) added $1M of his own. The same agenda: Two days after the midterms, ARI led 52 groups urging Democrats to hand out committee chairs based on AI safety positions. The seat and power: With Democrats taking the House, ARI is pushing hard for Grace Meng to chair the Commerce, Justice, Science (CJS) Appropriations subcommittee— the panel that funds the Department of Commerce (@CommerceGov). Commerce runs AI chip export controls and @NIST's AI safety work: Anthropic's top two priorities in Washington. Now she's going after NVIDIA—Anthropic's fiercest rival on export controls—and Commerce, the very agency she'll fund. Same donors. Same operative. Same agenda. Same subcommittee. No law needs to be broken. Interests find power. Power finds interests. That's the five-alarm fire. The real one. Congresswoman, you asked for full transparency. Here it is.

Congratulations, Anthropic. The company that sells "AI safety" just made AI a lot safer: for Anthropic. You couldn't out-build Jensen Huang, so you out-lobbied him. Your PAC paid the senator. Your China fears wrote the chip curbs. The press did the rest. The man who built the chips your models run on is out. Your IPO is this week. Pure coincidence, surely. Anyone thinking of buying into this IPO should ask one question: if this is how Anthropic treats its own supplier, how will it treat you? "For they have sown the wind, and they shall reap the whirlwind." — Hosea 8:7

Huge AI announcements from OpenAI, Anthropic, Meta, and Google in the past 48 hours. Here's everything going on in AI right now: 1. The authors of AI 2027 just moved their timelines up. They now expect AI on par with the best human AI researchers to arrive in 2027, after METR estimated Anthropic is improving about 2x as fast thanks to AI. Daniel Kokotajlo gives it a 50-50 chance by May 2027 and says he's "scared, sad, and angry." 2. Anthropic opened the investor pitch for its IPO, with shares likely trading as soon as Thursday next week. An updated filing also says it has now crossed its own safety line for AI-driven progress. 3. OpenAI launched Businesses in ChatGPT, a beta hub where brands can set up AI agents for shoppers, claim a verified profile, and track how often ChatGPT mentions them. Paid ads can point users to those agents too. This is like the start of SEO for chatbots. 4. Anthropic rolled out Claude Sheets and Whiteboards in beta, made Claude Data generally available, and announced Claude Meetings, an assistant that sits in on your video calls. Add those to Slides, Design, and Docs. Seems like Claude is slowly rebuilding the entire office suite. 5. Anthropic also released Claude Fable 5.2 and Mythos 5.2 yesterday, with Fable debuting at #1# on Artificial Analysis' Intelligence Index, 5 points ahead of Google's Gemini 4 Carbon. It's also 20% cheaper and up to 30% faster than 5.1. Google lost the top spot before Carbon even shipped (!) 6. Meta released Muse Ember, its smallest model, built for high-volume agent work. It ties Claude Haiku 5.5 on the Intelligence Index at roughly one-third of the cost per task ($0.14 vs. $0.41 on an average test). Meta shipped its first Muse model in April and now has an answer for every tier OpenAI and Anthropic sell. 7. Google announced 2 new AI chips coming next year: the TPU 8tx, which keeps data encrypted even while a model is working on it, and the 8i Max, which joins 2 chips into one for agents that need to hold an entire codebase in view. Google already has nearly 100 TPU customers (including Anthropic and Apple) and every available chip is spoken for. 8. Nvidia's top lawyer reportedly emailed agents in August 2025 while they were investigating whether Singapore's Megaspeed smuggled its chips to China. The Commerce Department then halted the case and handed it to the Justice Department. Not a great week for Nvidia. 9. Adobe signed a multi-year deal with Disney to build custom AI models trained on Disney's characters and visual styles, with work already underway for theme parks, film, and ESPN. Pretty interesting to see one of the most protective IP owners in entertainment is now training its own AI models. 10. OpenAI acquired Odessia, a months-old AI trip-planning startup from Sonder founder Francis Davidson, who is joining OpenAI to work on travel. Between this and #3#, ChatGPT is coming for shopping and travel. 11. France unveiled the Paris Call for AI Safety and Security, with OpenAI, Anthropic, and Mistral committing to build emergency off switches into their most advanced models. Interesting timing given #1# on this list. Daily reminder that this is the worst AI will ever be.

“We believe the world should accept some bad things happening for the benefits of this technology.” In a conversation for the first edition of Decoded, a new daily newsletter and podcast, OpenAI CEO Sam Altman talked with POLITICO’s @BrendanBordelon about trade-offs, AI safety, and how his company is different from Anthropic. Subscribe to Decoded for the full conversation with Sam Altman:

The interview with @thsottiaux from OpenAI 🔥 0:00 Everything OpenAI launched at DevDay 2:44 Sponsors: Wispr Flow, Hostinger, OpenArt 4:11 What is ChatGPT Dots? 7:52 Will ChatGPT Dots be free? 10:15 GPT-6.1 Sol vs GPT-6 Astra 11:44 Is AI now building AI? 12:53 Ultra Fast: when does everyone get it? 14:00 How OpenAI rebuilt the ChatGPT desktop app in 30 days 19:08 Why everything will run in the cloud 20:55 Calling your Dots on the phone 22:11 The new Turing test 24:05 OpenAI's mission and AI safety 26:14 Why OpenAI still works like a startup 27:29 The truth about ChatGPT usage resets 29:00 The $500 ChatGPT plan 30:17 Sponsors in action 32:23 Why AI agents still fail 33:52 OpenAI's AI is now on call 34:26 OpenAI's internal benchmarks 35:55 Open source Codex and the open ecosystem 38:42 ChatGPT Space explained 39:45 Is the chat box holding AI back? 42:26 Every DevDay update, full workshop 43:28 How people really use ChatGPT Work and Codex 44:01 When is the next OpenAI model coming? 45:05 What AI has to solve next 45:32 Is your job safe from AI? 48:14 Rapid fire 48:54 Has OpenAI already reached AGI? 50:48 The one thing he'll never let AI do 51:22 His morning AI routine 52:15 What he'd build if not AI Watch the full podcast on YouTube or X. Enjoy!