433 articles tagged with Safety/Alignment
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe. Subscribe no...
A look at the structural improvements in version 1.9.0 — and why an MIT-licensed red teaming...
Entrepreneurs have heard for years that artificial intelligence will change how companies operate. In many ways, that prediction has already come true. AI can draft emails, summari...
司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents
Singapore's Infocomm Media Development Authority and Microsoft signed a memorandum of understanding to strengthen their collaboration on artificial intelligence safety and security...
We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip. The released che...
Fable jailbreak?: Swift shutdown of Anthropic's new LLM may have been based on Amazon researchers figuring out how to circumvent safeguardshttps://www.theverge.com/ai-artificial-in...
The Trump administration restricted access to Anthropic's Mythos 5 AI modEl after Amazon researchers jailbroke it, citing national security concerns. The move has sparked debate ov...
'It's not a jailbreak' — Research leading to U.S. export restrictions on top Anthropic models was for defense, cybersecurity CEO says | Fortune"It was Defense Oriented Prompting (D...
A new CVE against Cursor, a LiteLLM supply-chain backdoor, and a study showing image-only injection...
Anthropic says all AI models can be hacked."We suspect that perfect jailbreak resistance is not currently possible for any model provider." "...it is likely that universal jailbrea...
Anthropic’s Fable Is Locked Down As US Takes AI Safety Into Its Hands Matteo Della Torre/NurPhoto via Getty Images Fable 5 became collateral damage on Friday evening at 5:21 pm per...
The Fable 5 Jailbreak Shows Why AI Guardrails Alone Are Not Enoughhttps://www.agilehunt.com/blog/fable-5-jailbreak-ai-guardrails#HackerNews #Tech #AI
Open claude.ai and it reads, “Claude Fable 5 is currently unavailable.” Click on ‘Know More’ and the website redirects to its maker Anthropic’s statement explaining the US governme...
OpenAI, the company behind ChatGPT, is being investigated by a coalition of 42 U.S. state attorneys general over its business practices, user safety measures and handling of consum...
Human psychology tricks can bypass AI safety guardrailshttps://www.psypost.org/human-psychology-tricks-can-bypass-ai-safety-guardrails/#ai
A coalition of US state attorneys general is investigating OpenAI amid growing concerns over AI safety, accountability, and user harm.
The fast-moving world of artificial intelligence just hit its first massive regulatory brick wall, and it is unlike anything we have seen before. In an unprecedented move, Anthropi...
UCLA Health launched the INOVAi Center on June 11, 2026, to test AI safety in clinical care. Trials show AI scribes cut physician note-writing time and reduce exhaustion.
This also implies the Alignment Problem of keeping #AI to human goals is intractable without constant human input, as model collapse will always pull towards the unaligned minima o...
Microsoft has signed a memorandum of understanding to collaborate with Singapore's Infocomm Media Development Authority on artificial intelligence safety and security, the latter s...
Bingo - AI-powered Red Team Terminal (DeepSeek/Claude/GPT/GLM)
A former xAI engineer has accused Elon Musk's artificial intelligence company of dismissing him after he repeatedly warned about the risks posed by Grok. The lawsuit paints a pictu...
📰 A former xAI engineer has filed a lawsuit against the company and SpaceX, alleging he was fired for raising AI safety concerns about Grok days before SpaceX's historic IPO.🔗 http...