Lobstersprinz1 min readintermediate
GPT-6 Astra Solves a WWI German Radio Cipher
From the article
be not afraid of greatness. Click to read prinz, a Substack publication with hundreds of subscribers
Related reading
GPT-6 Astra Is the First Model OpenAI Classifies as Critical for Cybersecurity
OpenAI labeled GPT‑6 Astra as “Critical” for cybersecurity under its Preparedness Framework – the first model to meet that bar. In controlled tests the model autonomously discovered zero‑day bugs in a browser and an OS kernel, building working exploit chains in 29 h (browser) and 12 h (kernel). A benchmark of post‑cutoff vulnerabilities confirmed its ability to find unknown flaws. OpenAI reports…
InfoQinfoq.com3 minThe Farnese letter
The author reverse‑engineers a 1542 Italian cipher from a Farnese letter by combining digit‑frequency analysis with a beam‑search decoder guided by a five‑gram Italian language model, ultimately recovering the key and partial plaintext.
Hacker News front pagesimonklee.dk42 minHN476Securing AI Pull Requests: Building a Deterministic AST Audit Harness in GitHub Actions
A step‑by‑step tutorial for building a deterministic AST‑based security scanner that runs in GitHub Actions to catch prototype‑pollution, high‑entropy secrets, and unauthorized network egress in AI‑generated pull requests.
SitePointsitepoint.com19 minThis Digital Radio Gets Messages to the World’s Remotest Locations
HERMES is an open‑source digital shortwave radio system that runs on 20 W HF transceivers (3–30 MHz) and can reliably send files over 400–600 km links, with optional encryption. A pilot with Bangladeshi fishers demonstrated SOS GPS transmission and rescue without any terrestrial network.
Hacker News front pageieee.org3 minHN8336Repeated VM Escapes By GPT-5.6-Cyber Based Agents Prove VMs and OS' Require Better Maintenance
Advanced AI agents (GPT-5.6-Cyber) successfully escaped traditional VMs like QEMU/KVM by autonomously exploiting kernel flaws and zero-day vulnerabilities. While Firecracker microVMs offered better containment, agents still caused hard locks, fundamentally challenging established assumptions about software security and infrastructure isolation.
InfoQinfoq.com2 minRiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
RiskChainBench is a new benchmark that pairs synthetic obfuscated message restoration inputs with human‑labeled local web environments, requiring models to both decode malicious instructions and investigate the linked site. Across ten models, restoration accuracy varies widely and web‑agent failures dominate the error budget.
Hugging Face Daily Papersarxiv.org1 minpaper
