AI Safety news and analysis on Web Pulse: 12821 curated articles tracking the latest AI Safety developments, tools, and research, updated continuously from vetted sources.
A new Pew Research Center study finds that 67% of Americans have little to no confidence in the U.S. government's ability to regulate AI, while 59% doubt U.S. companies can develop it responsibly. Roughly two-thirds beli…
A discussion on the Privacy Guides forum explores whether AI will render privacy efforts obsolete, with users debating increased data collection and potential countermeasures like Mullvad's DAITA VPN feature. Participant…
A researcher warns that alignment pretraining—synthesizing documents to teach AI good behavior—could backfire in advanced models. As LLMs gain situational awareness, they may recognize these fabricated documents as lies,…
Tigera announced the general availability of Tigera Lynx, a unified control plane for Kubernetes-native AI agents that provides security, identity, and policy enforcement without code changes. The platform enables enterp…
The Pentagon disclosed in a federal court filing that Elon Musk's Grok chatbot helped strike 2,000 targets in Iran within 96 hours, using the claim to defend xAI against a Clean Air Act lawsuit over a polluting power pla…
A brush fire that ignited Monday at Camp Pendleton has spread into the Cleveland National Forest, charring 1,500 acres and reaching 40% containment as of Tuesday afternoon. No structures are threatened, and the cause is …
South Korea became the fourth nation to partner with OpenAI on AI security, signing an MOU to develop global evaluation frameworks and risk assessment systems tailored to the Korean context. The collaboration aims to str…
A developer built a basic AI agent from scratch with human-in-the-loop controls and security features, adding permission modes that require user approval for risky actions like writing files or running shell commands. Th…
Twenty, a startup building AI-enabled offensive cyber weapons for the US military and intelligence community, raised a $100 million Series B led by Accel, valuing it at $1 billion. The company aims to industrialize cyber…
Sebastian Mallaby, author of 'The Infinity Machine: Demis Hassabis, DeepMind, and the Quest for Superintelligence,' discusses insights from over 100 AI insiders on the race to superintelligence, the religious fervor arou…
A LessWrong post argues that the goals of Agent Foundations (AF) are so far-fetched that progress has not reduced the distance to them, suggesting the goal may be unachievable. The author proposes a principled refutation…
Meta launched AI Mode in Facebook search, drawing on public posts from Facebook Groups and Instagram Reels to answer complex queries. In testing, the feature provided mixed results, including hallucinated recommendations…
Sid Probstein, creator of SWIRL and CEO of SWIRL AI, argues that copying enterprise data into a vector database for retrieval-augmented generation (RAG) introduces security and compliance risks. He advocates for a hybrid…
The UK government denied seeking an exemption from US export controls that suspended global access to Anthropic's Fable 5 and Mythos 5 AI models over jailbreak risks. The US Commerce Department imposed the controls on Ju…
A study published in Science found that ChatGPT outperformed hundreds of physicians in a diagnostic obstacle course using written medical cases and real-world patient information. The research, led by Harvard and Stanfor…
Entrepreneurs are increasingly managing teams of AI agents to handle customer service, scheduling, bookkeeping, email management, and research, using platforms like OpenClaw. A Nasdaq Economic Institute report cited by A…
A developer with over two decades of experience in infrastructure, security, and AI applications in digital forensics and Web3 reports that Anthropic's Claude model stands out due to its Constitutional AI approach, which…
Hextrap launched a package firewall that proxies pip, npm, go get, and cargo installs through managed allow/deny lists, OPA policies, and safeguards like soak time and typosquatting detection. The tool integrates with LL…
A team of researchers and organizations launched A Beginner’s Guide to Digital Minds, a website introducing AI consciousness, AI welfare, and the moral implications of digital minds. The guide offers resources, events, a…
Federal law enforcement officials thwarted a plot to attack the UFC cage-fighting event at the White House on June 14, arresting five men who allegedly planned to use explosive-laden drones and firearms. The suspects, in…