2026
- Weekly Review โ Oct 26โNov 1, 2026
TL;DR: Four posts this week, and three of them are about what an agentโs safeguards actually rest on. I ran my own agent setup through Shostackโs four threat-modeling questions. Most of my rules came โฆ
- Who Threat-Models the Vulnerability Harness?
TL;DR: AWS has published a two-part series on an AI vulnerability harness. The pipeline narrows scanner output to a short list of evidence-backed findings, and a steering file tells the model how to โฆ
- My Agent's Rulebook Was an Accidental Threat Model
TL;DR: Almost every safety rule in my personal agent setup got written the day after something went wrong. I ran the whole setup through Shostackโs Four Question Framework (what are we working on, โฆ
- Who Referees the AI?
TL;DR: In July 2026 a purported disproof of the Collatz conjecture got through Leanโs official proof checker, and through an independent second checker as well. It was wrong. The submission exploited โฆ
- Foundations of Agent Authorization
TL;DR: Agent authorization looks like a scary new frontier, but almost all of it is OAuth 2.0 and OpenID Connect, the same flows that already sign you into web apps. Once you can tell apart the three โฆ
- When the SOC Analyst Is an Agent
TL;DR: Amazon GuardDuty now ships an AI investigation agent (in preview) that takes a raw finding, pulls 90 days of related activity, correlates it against threat intel and a knowledge graph, and โฆ
- Post-Quantum Crypto Is Here โ What It Means on AWS
TL;DR: Post-quantum cryptography stopped being a research-paper topic. The reason to care today is โharvest-now, decrypt-laterโ: an adversary records your encrypted traffic now and decrypts it once a โฆ
- MCP Strategies on AWS, Part 4: Governance in Code
TL;DR: The governance pillar of the AWS MCP guidance has the best whiteboard story in the whole document, so I made it runnable. The story: an admin asks an agent to clone a production database, the โฆ
- The 732-Byte Wake-Up Call
Security is not a phase you pass through on the way to production. It is a permanent condition. On April 29, 2026, a security research team published a vulnerability that works on every Linux โฆ
- Security Is Job Zero โ Even (Especially) in the Age of Coding Agents
$20 and Two Hours On February 28, 2026, security startup CodeWall gave an autonomous AI agent a single input: a domain name. Two hours and approximately $20 in API tokens later, the agent had full โฆ
- ๐ ๐๐ฃ ๐ง๐ผ๐ผ๐น ๐๐ต๐ฎ๐ผ๐ - ๐ด๐ผ๐ ๐น๐ผ๐๐ ๐ถ๐ป ๐ฎ๐๐๐ต๐ฒ๐ป๐๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป ๐ฎ๐ป๐ฑ ๐ด๐ผ๐๐ฒ๐ฟ๐ป๐ฎ๐ป๐ฐ๐ฒ?!
๐ ๐๐ฃ ๐ง๐ผ๐ผ๐น ๐๐ต๐ฎ๐ผ๐ - ๐ด๐ผ๐ ๐น๐ผ๐๐ ๐ถ๐ป ๐ฎ๐๐๐ต๐ฒ๐ป๐๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป ๐ฎ๐ป๐ฑ ๐ด๐ผ๐๐ฒ๐ฟ๐ป๐ฎ๐ป๐ฐ๐ฒ?! Agentic coding has become reality for developers everywhere ๐. Tools like Anthropicโs Claude Code and Amazonโs Kiro are leading the charge, โฆ
- Argh - My AI Agent deleted all my files
๐ฑ โArgh - My AI Agent deleted all my files!!!!  ๐ฑ โArgh - My AI Agent deleted all my files!!!!โ Created on 2026-01-16 06:53 Published on โฆ
- ๐ฑ ๐๐ฟ๐ด๐ต - ๐ ๐ ๐๐ ๐๐ด๐ฒ๐ป๐ ๐ฑ๐ฒ๐น๐ฒ๐๐ฒ๐ฑ ๐ฎ๐น๐น ๐บ๐ ๐ณ๐ถ๐น๐ฒ๐!!!! Worried about AI agents running amok with your data? Before panicking
๐ฑ ๐๐ฟ๐ด๐ต - ๐ ๐ ๐๐ ๐๐ด๐ฒ๐ป๐ ๐ฑ๐ฒ๐น๐ฒ๐๐ฒ๐ฑ ๐ฎ๐น๐น ๐บ๐ ๐ณ๐ถ๐น๐ฒ๐!!!! Worried about AI agents running amok with your data? Before panicking, consider this: weโve been solving permission and access control problems for โฆ
- โGood Morning! said Bilbo, and he meant it. The sun was shining, and the grass was very green. But G
โGood Morning!" said Bilbo, and he meant it. The sun was shining, and the grass was very green. But Gandalf looked at him from under long bushy eyebrows that stuck out further than the brim of his โฆ
2025
- ๐ ๐๐ฟ๐๐ฝ๐๐ผ๐ด๐ฟ๐ฎ๐ฝ๐ต๐ ๐ถ๐ป ๐๐ต๐ฒ ๐ค๐๐ฎ๐ป๐๐๐บ ๐๐ด๐ฒ: ๐ฆ๐๐ฎ๐ฟ๐๐ถ๐ป๐ด ๐ก๐ผ๐
๐ ๐๐ฟ๐๐ฝ๐๐ผ๐ด๐ฟ๐ฎ๐ฝ๐ต๐ ๐ถ๐ป ๐๐ต๐ฒ ๐ค๐๐ฎ๐ป๐๐๐บ ๐๐ด๐ฒ: ๐ฆ๐๐ฎ๐ฟ๐๐ถ๐ป๐ด ๐ก๐ผ๐ Yesterday I had the pleasure to listen to and discuss with my colleagues Sviatoslav Redko and Viacheslav Romanov during their talk โCryptography in the โฆ
- Do You Know What Your AI Agents Are Doing? Lost Control? ๐ค
Do You Know What Your AI Agents Are Doing? Lost Control? ๐ค While having a 2nd coffee - to be honest, itโs the third already as days are long at #MTM25 - Iโm reflecting on what has been top of mind for โฆ
2024
- โ๏ธ In my conversation with customers, I don't get tired in highlighting how important it is to decompose
โ๏ธ In my conversation with customers, I donโt get tired in highlighting how important it is to decompose applicationโs needs into the different use cases and choose the best-fitting foundation model โฆ
- What happens in Las Vegas ... Nah - let's have a look. All things (Gen) AI.
What happens in Las Vegas โฆ Nah - letโs have a look. All things (Gen) AI.  What happens in Las Vegas โฆ Nah - letโs have a look. All things (Gen) AI. โฆ
2023
- Today content monetisation still largely depends on 3rd party data while the technical foundation, 3
Today much of ad-funded content monetisation still leans on 3rd party data, while the technical foundation of its browser-based collection, 3rd party cookies, is on the way out: some browsers already โฆ