KB Incidents Series' Articles

Delafosse Olivier

May 27

Inside the First AI‑Crafted Zero‑Day: How Google Blocked a 2FA Bypass and What It Means for Your LLM Security Stack

#ai #machinelearning #llm #programming

8 min read

Delafosse Olivier

May 28

Inside the Claude Code 512K Leak: What Anthropic’s npm Mistake Reveals About Real-World AI Agent Architecture

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

May 28

Anthropic Mythos vs OpenAI GPT-5.5: How Frontier LLMs Are Changing Software Hacking and How to Defend

#ai #machinelearning #llm #programming

6 min read

Delafosse Olivier

May 29

How ServiceNow Uses AI and Automation to Power the Agentic Enterprise

#ai #machinelearning #llm #programming

6 min read

Delafosse Olivier

May 29

GPT‑5.5‑Cyber vs Anthropic Mythos: Scrutinizing Hacking‑Capable AI in Production

#ai #machinelearning #llm #programming

10 min read

Delafosse Olivier

May 29

Inside Grok V9-Medium 1.5T: Architecture, Deployment, and Production Playbook

#ai #machinelearning #llm #programming

8 min read

Delafosse Olivier

May 29

Anthropic Mythos vs OpenAI GPT‑5.5‑Cyber: How Hacking-Capable AI Is Redefining Cybersecurity and Governance

#ai #machinelearning #llm #programming

8 min read

Delafosse Olivier

May 29

Anthropic Mythos vs OpenAI GPT‑5.5: Are Hacking‑Capable LLMs a Cybersecurity Time Bomb?

#ai #machinelearning #llm #programming

6 min read

Delafosse Olivier

May 30

Inside Japan’s Digital Agency GENAI Stack for Secure Government AI

#ai #machinelearning #llm #programming

6 min read

Delafosse Olivier

May 30

Grok V9-Medium: 1.5T Model Architecture & MLOps Guide

#ai #machinelearning #llm #programming

8 min read

Delafosse Olivier

May 30

Anthropic Mythos vs OpenAI GPT‑5.5‑Cyber: Hacking‑Capable AI Under Security Scrutiny

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

May 30

Anthropic Mythos vs OpenAI GPT‑5.5‑Cyber: Architecting with Hacking‑Capable AI Models Safely

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

May 30

Anthropic Mythos vs OpenAI GPT‑5.5: Are ‘Hacking‑Capable’ Frontier Models a Cybersecurity Time Bomb?

#ai #machinelearning #llm #programming

6 min read

Delafosse Olivier

May 31

Anthropic Mythos vs OpenAI GPT‑5.5: How to Engineer with Hacking‑Capable AI Under Scrutiny

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

Jun 1

OWASP GenAI Q1 2026 Exploit Round-up: From Flowise RCE to Claude-Assisted Breaches

#ai #machinelearning #llm #programming

8 min read

Delafosse Olivier

Jun 1

How an AI Coding Agent Triggered a Recursive Deletion Disaster in May 2026 (and How to Architect for Failure Containment)

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

Jun 1

ClawHavoc Exposed: How 824 Malicious LLM Skills Infected the OpenClaw Marketplace

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

Jun 2

Designing with MiniMax M3: Architecting Long‑Context AI Coding Systems That Actually Ship

#ai #machinelearning #llm #programming

6 min read

Delafosse Olivier

Jun 2

May 2026 Enterprise AI Hallucination Crisis: How Automated Workflows Broke and How to Fix Them

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

Jun 3

Inside Sysdig’s First Documented LLM-Agent-Driven Cyber Intrusion: An Engineering Playbook

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

Jun 3

Inside the First LLM-Agent-Driven Cyber Intrusion: How an AI Operator Exfiltrated a Database in Under an Hour

#ai #machinelearning #llm #programming

10 min read

Delafosse Olivier

Jun 3

Inside the First LLM-Agent-Driven Cyber Intrusion: What Sysdig’s Case Changes for SOC Automation

#ai #machinelearning #llm #programming

10 min read

Delafosse Olivier

Jun 3

How a Meta AI Support Bot Could Be Hijacked to Steal Instagram Accounts via Prompt Injection

#ai #machinelearning #llm #programming

9 min read

Delafosse Olivier

Jun 3

Inside the Meta AI Support Bot Prompt Injection Hack: How Attackers Hijacked High-Profile Instagram Accounts

#ai #machinelearning #llm #programming

8 min read

Delafosse Olivier

Jun 4

Trump’s New AI Executive Order: What Early Federal Access to Models Would Mean for ML Engineering

#ai #machinelearning #llm #programming

6 min read

Delafosse Olivier

Jun 5

Meta’s AI Model Delay: What It Means for Developers, Security, and Production Roadmaps

#ai #machinelearning #llm #programming

7 min read

Delafosse Olivier

Jun 5

How BadHost Auth Bypass in Starlette Can Expose Your AI Agents

#ai #machinelearning #llm #programming

5 min read

Delafosse Olivier

Jun 6

Inside the University of Toronto’s Open-Weight AI Worm: Architecture, Risk Model, and Defensive Playbook

#ai #machinelearning #llm #programming

7 min read

Delafosse Olivier

Jun 7

Sam Altman, AI Pre-Approval, and What US Builders Should Really Expect from Washington

#ai #machinelearning #llm #programming

7 min read

Delafosse Olivier

Jun 7

How Enterprise LLM Development Companies Build Production-Ready AI Systems

#ai #machinelearning #llm #programming

8 min read