Security & Safety
Two H100s Are Enough, Command A+ Targets Private Agents
Cohere Command A+ lowers the bar for private AI agents with Apache 2.0 open weights and a two-H100 deployment target.
← All categories
Security & Safety
Vulnerabilities, prompt injection, model safeguards, and containment design.
Security & Safety
After 10,000 vulnerabilities, Mythos moves the bottleneck to patching
Anthropic Project Glasswing shows that AI vulnerability discovery is no longer the slowest step. Verification, disclosure, and patch rollout are now the constraint.
Security & Safety
OpenAI adopts SynthID as AI image trust gets a new baseline
OpenAI and Google are turning C2PA, SynthID, and verification tools from image-generator features into web-scale trust infrastructure.
Security & Safety
Claude Gets a Conscience Tool, and Alignment Moves Into the Agent Loop
Anthropic is widening the moral formation conversation around Claude while testing an ethical reminder tool inside the model runtime loop.
Security & Safety
28 Security Integrations Put Claude in the AI Audit Log Era
Anthropic expanded Claude Compliance API integrations into the enterprise security stack. AI chats, files, and activity logs are becoming audit pipeline inputs.
Security & Safety
Falco Steps In Before Coding Agents Call Tools
Prempti is a new Falco experiment that evaluates coding-agent tool calls before Claude Code and similar agents execute them.
Security & Safety
RAMPART Turns Prompt Injection Into an Agent Safety Test
Microsoft RAMPART and Clarity Agent move agent safety from late-stage review into CI tests, design records, and pull request evidence.
Security & Safety
Claude agents enter the private network, with execution kept inside
Claude Managed Agents added self-hosted sandboxes and MCP tunnels, redrawing the enterprise boundary between orchestration, execution, and audit.
Security & Safety
Full repo scanning, the SAST gap AWS Security Agent is targeting
AWS Security Agent full repository code review targets trust boundaries and data flows that traditional SAST often misses.
Security & Safety
Composer 2.5 shows Cursor training for reward hacking
Cursor Composer 2.5 shows the coding-agent race shifting from benchmark scores toward long-task failure points, targeted feedback, and reward-hacking detection.
Security & Safety
Why OpenAI replaced certificates after signed malicious packages
The TanStack npm incident reached OpenAI Codex and ChatGPT Desktop certificate rotation, showing how AI development tools now inherit supply-chain trust risk.
Security & Safety
The My Lord recruiting bot exposed the real AI hiring risk
A LinkedIn profile prompt injection changed automated recruiting messages. The deeper issue is what happens when resumes and profiles become agent input.