Clean GitHub repo tricks AI coding agents into running malware

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
winbuzzer.com

OpenAI Says GPT-5.5-Cyber Leads Claude Mythos, Expands Daybreak-Initiative

OpenAI is now turning its Daybreak initiative into a defensive cybersecurity program that combines Codex updates, the GPT-5.5-Cyber release and partner access for approved organizations. As OpenAI ...

The maker of ChatGPT wants to make open-source projects less of a security bargain

As AI tools flood open-source maintainers with low quality bug reports, OpenAI's new Patch the Planet initiative aims to filter out the noise and fix real threats.

OpenAI's new GPT-5.5-Cyber tops Claude Mythos 5 in vulnerability benchmark0 0

OpenAI is rolling out the full, limited-release version of GPT-5.5-Cyber—a specialized AI model that outperforms its ...
Ars Technica

512-bit RSA key in home energy system gives control of “virtual power plant”

When Ryan Castellucci recently acquired solar panels and a battery storage system for their home just outside of London, they were drawn to the ability to use an open source dashboard to monitor and ...
GitHub

Source code for the paper Learning the greatest common divisor: explaining transformer predictions

This directory contains the source code for the paper Learning the greatest common divisor: explaining transformer predictions (ICLR 2024). To run the program: python train.py --dump_path MYPATH --exp ...
GitHub

Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate (ICLR 2025)

Abstract: Remarkable progress in text-to-image diffusion models has brought a major concern about potentially generating images on inappropriate or trademarked concepts. Concept erasing has been ...