Updated daily503 verified stories
Safety News tracker.
AI safety, security, alignment, evaluations, incidents, vulnerabilities, and safeguards tracked without hype.
- 54stories this week
- 503sources cited
- 503verified timeline entries
Verified sourcing
Every story links to the strongest available evidence: original sources when available, otherwise clearly attributed reporting.
Plain English
What happened, why it matters, and what to watch — without the jargon.
No filler
When the signal is thin, we publish nothing rather than padding the feed.
More stories
9 storiesSecurity
Preprint proposes adaptive safety shields for reinforcement-learning agents
A new preprint proposes updating safety constraints for reinforcement-learning agents as they learn unknown transition probabilities, potentially extending probabilistic shielding to settings where the environment model is incomplete.arxiv.orgSecurity
Google Cloud Details CodeMender AI Agent for Code Vulnerability Remediation
Google Cloud presents CodeMender as an AI security agent that scans codebases, tests whether vulnerabilities can be exploited, and generates patches for developer review. The source does not describe it as a formal-verification framework or provide independent performance evidence.
cloud.google.comSecurity
Anthropic expands Claude Mythos 5 for cyber defense and pledges $35 million in open-source credits
Anthropic says Claude Mythos 5 is now powering vulnerability scans in Claude Security for Enterprise customers, while partner integrations are planned. It is also creating a $35 million credit fund for open-source security and expanding its cyber-verification program.claude.comSecurity
NVIDIA says AI-agent security should sit below the harness
NVIDIA argues that AI-agent security controls should be enforced by runtimes and infrastructure, rather than by modifiable model or harness logic. Its technical blog proposes a layered architecture and four workload profiles, but provides no independent validation of the approach.
developer.nvidia.comSecurity
Open-source app warns about nearby smart glasses, but its signals are only a rough proxy
The Nearby Glasses project uses Bluetooth data to flag some smart-glasses devices on Android and iOS. Its own documentation says the system can produce false positives, miss devices and should not be used to confront people.github.comSecurity
Google Threat Intelligence reports AI-assisted vulnerability research and autonomous malware
Google Threat Intelligence Group says adversaries are using AI to accelerate vulnerability research, evade detection, automate malware actions and target the software supply chain around AI systems.cloud.google.comSecurity
Preprint reports language-model outputs can leak secrets held in context
An arXiv preprint reports that language models may reveal sensitive data placed in context, even after refusing direct extraction requests. In controlled experiments, the authors say adaptive attacks recovered short secrets from ordinary outputs and extracted full Social Security numbers from a production-style agent.arxiv.orgSecurity
Study Finds Denoising Can Recover More Text From Noise-Protected Embeddings
A paper accepted by IEEE ICDM 2026 reports that adaptive inversion reconstructs substantially more of the original text from Gaussian-noise-protected embeddings than an existing generative baseline, challenging a widely used privacy assumption without establishing real-world exposure or independent replication.arxiv.orgSecurity
Ph.D. dissertation examines backdoor attacks in language and vision-language models
An arXiv-listed Ph.D. dissertation studies how backdoor attacks can affect language models and vision-language models, including methods for analysis, detection and attack design.arxiv.org
One useful briefing each week
Keep up with AI without living in the feed.
Get the week’s verified AI news, original data, useful tools, learning picks, and fresh AI jobs.
Reach people who are learning AI
Hiring an AI professional or launching a useful AI product? Put it in front of people who came here to learn and act.
Post an AI jobSubmit an AI tool