By
–
gave an agent access to my actual stack today
— Nico (@nicos_ai) 24 juin 2026
no scary “it can see everything” moment. scoped permissions, every action logged
felt illegal how clean it was https://t.co/xeAVrovr1D pic.twitter.com/NyPzYIQWf3
gave an agent access to my actual stack today no scary “it can see everything” moment. scoped permissions, every action logged felt illegal how clean it was
By
–
gave an agent access to my actual stack today
— Nico (@nicos_ai) 24 juin 2026
no scary “it can see everything” moment. scoped permissions, every action logged
felt illegal how clean it was https://t.co/xeAVrovr1D pic.twitter.com/NyPzYIQWf3
gave an agent access to my actual stack today no scary “it can see everything” moment. scoped permissions, every action logged felt illegal how clean it was
By
–
/5 OpenAI launches GPT-5.5-Cyber to scan, patch, and fix vulnerable code at scale. GPT-5.5-Cyber is a specialized model that scored 85.6% on CyberGym (vs 81.8% for standard GPT-5.5). It is gated to verified defenders only, not open access. Plugged into Codex, the new Codex
By
–
As AI-powered cyber threats evolve at unprecedented speed, strengthening cybersecurity resilience has become more critical than ever. To address this emerging challenge, CERT-In has issued new guidelines for OEMs and Technology Providers, focusing on AI-assisted vulnerability
By
–
Reuters has now added more context to last week's Mythos report. According to AP, Anthropic's Mythos model identified vulnerabilities in highly sensitive US government computer systems during a test exercise conducted
By
–
As Artificial Intelligence reshapes the digital world, it is also transforming the nature of cyber threats. Recognising this evolving landscape, CERT-In has released its Blueprint for Defending Against AI-Assisted Exploitation- a comprehensive framework to help organisations
By
–
Bien que Mythos ait popularisé l'idée de détecter des vulnérabilités avec les LLM, Aisle le faisait plus tôt. D'un point de vue ingénierie, il est intéressant de constater qu'un petit modèle à poids ouvert avec un système de recherche structuré est compétitif pour cette tâche.
By
–
Karpathy said something you'll regret ignoring:
— Akshay 🚀 (@akshay_pachaar) 23 juin 2026
"We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues."
He said it at YC talk last year, when the worry was reliability. The… https://t.co/qtbSsM5W8A pic.twitter.com/df5yjZmdO9
Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The
By
–
From @PacktDataML — available at http://
amzn.to/4sDpgxM "AI-Native LLM Security — Threats, Defenses, and Best Practices for Building Safe and Trustworthy AI" 𝘽𝙤𝙤𝙠 𝘿𝙚𝙨𝙘𝙧𝙞𝙥𝙩𝙞𝙤𝙣:
"Adversarial AI attacks present a unique set of security challenges, exploiting the
