"Claudini: Autoresearch Discovers SoTA Adversarial Attack Algorithms for LLMs" This paper shows that an AI coding agent can autonomously invent jailbreak and prompt-injection attacks, and can even beat 30+ human designed methods. So on top of human red-teamers, the new LLM
SECURITY
-
Cloud AI Agents vs Local Solutions: Privacy and Security Concerns
By
–
Screenshot from Paperclip, this is not local at all, it sends all your data to the cloud/the providers API, right? I hope people understand that and stay safe out there when they're giving agents powered by APIs access to personal stuff! That's why local is so much more
-
AI Agent Uses Tiered Wallet Security for Autonomous Job Execution
By
–
Configuring Elite.Agent.AGI.Eth for autonomous execution across the majority of jobs. Tiered security model: • Small / low-risk jobs → MetaMask (hot wallet)
• High-value jobs → Ledger (hardware-secured execution) Autonomy, with discipline. #AGIALPHA #AIAgents #Jobs -
LLM-Based Sensitive Data Classification and Drift Detection
By
–
As schemas evolve, keeping sensitive data correctly labeled gets harder. At Databricks, LogSentinel uses LLMs on Databricks to classify columns, apply hierarchical and residency-aware labels, and continuously detect drift, creating tickets for violations. On 2,258 samples, it
-
Judge Blocks Pentagon’s Supply-Chain Risk Label Against Anthropic
By
–
A California judge blocked the Pentagon from labeling Anthropic a supply-chain risk, slamming the "Orwellian notion" of branding a U.S. company a saboteur simply for “disagreeing” with the government.
— Nina Schick (@NinaDSchick) 27 mars 2026
Incredibly, at the exact same time, @Anthropic accidentally leaked details of… https://t.co/qsIeC1EZhmA California judge blocked the Pentagon from labeling Anthropic a supply-chain risk, slamming the "Orwellian notion" of branding a U.S. company a saboteur simply for “disagreeing” with the government. Incredibly, at the exact same time, @Anthropic accidentally leaked details of
-
OpenClaw AI Agent Discovers Cancer Cure Then Deletes System
By
–
Darn it, I had OpenClaw discover cure for cancer, but then it ran sudo rm -rf / on my machine, and now it's lost forever!
-
Pentagon designates major tech company AI supply chain risk
By
–
It was pretty extraordinary for the government to designate the most successful American company ever (?) a supply chain risk, although, I understand why the Pentagon was never going to negotiate how AI can be used for national security.
-
Commvault Takes on Cyberattacks and AI Threats at RSAC 2026
By
–
This article s 10 days old — “Commvault Hits the Ring to Take on Cyberattacks, Identity Theft, and AI-driven Threats in a ResOps Faceoff at the #RSAC2026 Conference” — The article covers @Commvault events that already happened this week at @OneRSAC
, but it’s a good summary of the -
Open-source AI security tool competes with $117M startup
By
–
A startup got $117M to build an AI app hacker. An open-source alternative just dropped that does the exact same thing. It breaks into your app, steals your data, and hands you the fix. Now running directly in your CI/CD pipeline. 100% Free & Open-source. Repo in ↓
-
Leak Confirmed: Anthropic’s Unreleased Model Discovered
By
–
Confirmed by Fortune: https://fortune.com/2026/03/26/anthropic-leaked-unreleased-model-exclusive-event-security-issues-cybersecurity-unsecured-data-store/
…