SecurityWeek

Researchers Demo New Claude Code Attack Using Harmless-Looking Repositories to Hijack Developer Machines

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
LinkedIn

Learn Deep Reinforcement Learning with Chelsea Finn

💡 New AI Course Alert! Deep Reinforcement Learning (XCS24R) taught by Chelsea Finn starts February 2, 2026. Ready to build AI that doesn't just predict, but acts? Every AI breakthrough—from ...
techtimes

Open-Source Coding Model Ornith-1.0 Writes Its Own Training Scaffold in Reinforcement Learning

DeepReinforce today released Ornith-1.0, a family of open-source coding models built around a mechanism most RL-trained agents avoid: the model itself writes the training harness that guides its own ...
IEEE

Differential High Order Control Barrier Function-Based Safe Reinforcement Learning

Abstract: Safe reinforcement learning (RL) aims to learn policy while also ensuring the safety constraints. An increasingly common approach is to design a safety filter based on control barrier ...