Millions of AI agents imperiled by critical vulnerability in open source package

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to ...

Valid certificates, stolen accounts: how attackers broke npm's last trust signal

Stolen credentials produced valid Sigstore certificates, clearing 633 malicious npm packages — one of seven developer tool ...
InfoQ

Designing AI Platforms for Reliability: Tools for Certainty, Agents for Discovery

Aaron Erickson discusses the evolution of AI workflows, shifting from "vibe checking" to building reliable, multi-agent ...
Geeky Gadgets

DeepSWE AI Coding Model Benchmark Finally Solves AI Training Data Contamination

DeepSWE, created by DataCurve offers a benchmark for assessing AI coding models by focusing on real-world programming challenges rather than synthetic test cases. According to Matthew Berman, one of ...

DeepSWE blows up the AI coding leaderboard, crowns GPT-5.5, and finds Claude Opus exploiting a benchmark loophole

DeepSWE puts GPT-5.5 atop the AI coding leaderboard while raising new questions about Claude Opus, SWE-Bench Pro, and ...
Geeky Gadgets

Inside the Self-Improving AI System Unlocking a Free 1-Million-Token Context Window

The integration of DeepSeek V4 with the Hermes Agent introduces a significant enhancement to open source AI capabilities. By combining a persistent, self-improving framework with advanced reasoning ...