AI Safety news and analysis on Web Pulse: 14015 curated articles tracking the latest AI Safety developments, tools, and research, updated continuously from vetted sources.
Webster Bank, a regulated financial institution, partnered with Varonis to protect over one million data resources and accelerate secure adoption of Snowflake and Microsoft Copilot, strengthening customer trust.
Common Sense Media launched its Youth AI Safety Institute on May 5, backed by a new initiative to address artificial intelligence risks for children. The nonprofit, known for technology recommendations for families, appo…
Microsoft has open-sourced two new tools, Rampart and Clarity, designed to integrate AI safety checks earlier into the agent development lifecycle. The tools aim to address risks such as prompt injection and privilege es…
On 20 May 2026, GitHub confirmed that approximately 3,800 internal repositories were exfiltrated after an employee installed a poisoned code editor extension that handed attackers credentials and cloud keys. The breach e…
Diciannove organizzazioni, tra cui Mozilla, The Tor Project, Proton, Mullvad VPN, ExpressVPN, IPVanish, Internet Society e EFF, hanno firmato una lettera aperta il 5 maggio 2026 rifiutandosi di implementare tecnologie di…
Nine malicious npm packages impersonating Polymarket trading tools were published on May 20, 2026, by the account "polymarketdev," stealing cryptocurrency wallet private keys upon installation. The packages execute a pos…
Financial AI initiatives often stall due to poor data foundations, not model flaws, according to experts Dr. Efi Pylarinou and Mike Sisk. Over 40% of financial firms still use spreadsheets, and fragmented data prevents r…
ChatGPT falsely confessed to a crime it could not have committed, highlighting the risks of relying on AI for factual accuracy. The incident underscores ongoing concerns about AI-generated misinformation in legal context…
Between 2024 and 2026, multiple major polls from Gallup, Pew Research Center, and other organizations show Americans have turned sharply against AI, with 71% opposing local data center construction and bipartisan concern…
Varonis announced its integration with AWS Security Hub Extended to provide unified, data-centric security across SaaS, multi-cloud, and hybrid environments. The partnership enables security teams to correlate sensitive …
Alice Ryhl, a software engineer on Google's Android Rust team and core maintainer of Tokio, discussed Rust's unique features and governance in a podcast episode. She highlighted that Rust's memory safety and compile-time…
Microsoft released two free, open-source security tools for developers on Thursday, addressing growing risks from AI agents that require increased data access and permissions. The tools, RAMPART and Clarity, embed red-te…
A vulnerability in Kubeflow versions prior to 1.10 allows attackers with Contributor or kubeflow-edit roles to steal authorization tokens via overly permissive Istio permissions, enabling account takeover and data access…
Nine application security startups debuted at RSAC 2026, responding to the collapse of traditional security boundaries caused by AI compressing the software development lifecycle. Companies like AppSentinels and Aurva ar…
A new analysis argues that the era of AI scaling producing clearly better models is ending, with frontier labs facing exponentially increasing costs for linear returns. The author claims that the internet has been fully …
1Password and OpenAI partnered to integrate 1Password as a trusted access layer for OpenAI's Codex, enabling just-in-time, scoped credential management that keeps secrets outside the model's context window. The integrati…
Developers risk losing core engineering instincts by relying too heavily on AI coding tools, according to multiple experts. Lars Faye warns that agentic coding prevents junior developers from building problem-solving ski…
NVIDIA launched verified agent skills to provide capability governance for autonomous AI agents, embedding transparency, provenance, security validation, and authenticity checks directly into the skill layer. The verifie…
Andrej Karpathy, a founding member of OpenAI and former Tesla Autopilot lead, joined Anthropic on May 19, 2026, to work on pre-training research focused on using Claude to accelerate its own improvement. The move signals…
The Trump administration is shifting from opposing AI regulation to considering a federal licensing regime for AI models, driven by growing public backlash and bipartisan support on Capitol Hill. President Donald Trump's…