Your hub for Ai Safety news and research — curated daily from 50 top AI sources including OpenAI, Anthropic, Google DeepMind, and more. Every article is reviewed and enriched with editorial analysis by the DeepTrendLab team.
May 13, 2026: Sam Altman testified against Musk while Google pushed Android AI into the mainstream. A fatal ChatGPT error and Meta's forced AI exposed the gap between speed and safety.
Standard prompt attacks are merely the beginning. A structured framework to map and mitigate the backend attack vectors of agentic workflows. The post The AI Agent Security Surface: What Gets…
Can Sam Altman—or any CEO—be trusted with super intelligence?
Two weeks ago, Anthropic announced that its new model, Claude Mythos Preview, can autonomously find and weaponize software vulnerabilities, turning them into working exploits without expert guidance. These were vulnerabilities…
Explore the GPT-5.5 Bio Bug Bounty: a red-teaming challenge to find universal jailbreaks for bio safety risks, with rewards up to $25,000.
ControlAI's mission is to avert the extinction risks posed by superintelligent AI. We believe that in order to do this, we must secure an international prohibition on its development. We're…
Training-based control studies how effective different training methods are at constraining the behavior of misaligned AI models. A central example of a case where we want to control AI models…
Code: github.com/ElleNajt/controllability tldr: Yueh-Han et al. (2026) showed that models have a harder time making their chain of thought follow user instruction compared to controlling their response (the non-thinking, user-facing…
Many people—especially AI company employees [1] —believe current AI systems are well-aligned in the sense of genuinely trying to do what they're supposed to do (e.g., following their spec or…
The model could help cybersecurity experts better prepare for attacks.
Sometimes people make various suggestions that we should simply build "safe" artificial Superintelligence (ASI), rather than the presumably "unsafe" kind. [1] There are various flavors of “safe” people suggest. Sometimes…
President Trump said during an interview aired yesterday by Fox Business that “there should be” when asked if AI needs […]
Many people—especially AI company employees [1] —believe current AI systems are well-aligned in the sense of genuinely trying to do what they're supposed to do (e.g., following their spec or…
It turns out that Anthropic accidentally trained against the chain of thought of Claude Mythos Preview in around 8% of training episodes. This is at least the second independent incident…
But Dr Heidy Khlaaf, chief AI scientist at the AI Now Institute and a former OpenAI safety engineer, is sceptical. She notes Anthropic provides no comparison with existing automated security…
Anthony Aguirre, President and CEO of the Future of Life Institute, issued the following statement in response to the attack […]
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv and feedback from readers. If you’d like to support this, please subscribe. Subscribe now Uh oh,…
Initial signatories include AI pioneers Yoshua Bengio and Geoffrey Hinton, leading media voices Steve Bannon and Glenn Beck, Obama's National Security Advisor Susan Rice, business trailblazers Steve Wozniak and Richard…
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv and feedback from readers. If you’d like to support this, please subscribe. A somewhat shorter issue…
Anthropic sues Trump administration in AI dispute with Pentagon, ‘Not built right the first time’ — Musk’s xAI is starting over again, again, Cascade of A.I. Fakes About War With…
Understanding the behavior of complex machine learning systems, particularly Large Language Models (LLMs), is a critical challenge in modern artificial intelligence. Interpretability research aims to make the decision-making process more…
OpenAI launches GPT-5.4 with Pro and Thinking versions, Google releases Gemini 3.1 Flash Lite at 1/8th the cost of Pro, Where things stand with the Department of War Anthropic
In April of 2025, OpenAI released a new version of GPT-4o, one of the AI algorithms users could select to power ChatGPT, the company’s chatbot. The next week, OpenAI reverted…
The collaboration will produce a Crisis Counselor Training Curriculum and a statewide AI Harms Reporting Form targeting dangerous AI companion applications