Blog
I Skipped the Handover
When someone new joined the team, I gave them no handover. I did not sit them down and walk through the shape of our systems, and I did not tell them what to install first. I handed over a link to an onboarding page, and that was all. Not long after, their development environment was standing. Credentials were in place, the internal services were connected, and they were running the team’s working workflow as it is. Except that the person did not perform that setup. They handed the onboarding page to an AI agent, said ‘set this up as written’, and the agent executed it from beginning to end.
2026-08-25
While We Waited for Quantum Computers, AI Arrived First
“AI just broke post-quantum cryptography.” That headline swept through the security community in late July, following an announcement from Anthropic that its model had found a key-recovery attack against HAWK-256, a NIST post-quantum signature candidate. The grammar of the reaction was familiar. The old dread — quantum computers will bring down every cipher at once — had returned, with only the subject swapped out for AI. In a previous post, I dismantled the quantum panic by classification: cryptography is not one monolith, and quantum computers topple only one side of it. The same tool applies here. Don’t stop at the verb ‘broke’ — separate precisely what broke from what did not.
2026-07-29
Is This My Writing?
A number from lcamtuf made the rounds, summing up Hacker News in a single line. In June 2026, roughly 55% of the daily top stories were either about AI or written by AI. Four months earlier, in February, it was 40%; now it had crossed the halfway mark. His method was simple. He classified the top stories by hand each day, ran the suspected ones through a detector, and verified the flags by eye.
2026-06-25
Proving Provenance Doesn't Stop Malicious Code
Lately the security world abroad has been busy over a single incident. On May 19, 2026, more than 300 malicious versions were published across 323 packages on the npm registry in the span of 22 minutes, reportedly. The key point is that no human did this. There was no attacker sitting at a keyboard infecting packages one by one. The code itself stole maintainer tokens, used those tokens to replicate itself into other packages, and stole more tokens from there — all without human intervention, the reports say. A self-replicating worm called “Shai-Hulud” is said to have spread through the npm ecosystem this way.
2026-06-18
Documents as a Neural Network: I Put a Ruler to My Own 'Second Brain'
Anyone who opens Obsidian’s graph view for the first time tends to freeze at the same picture: hundreds of dots tangled in lines, slowly pulsing, like a cross-section of a firing brain. It’s the exact screenshot every “second brain” pitch puts on its first slide. The promise: notes accumulate, they wire up like synapses, and at some point the system starts thinking for you. I believed that promise and piled up notes for nearly a year. A year later my graph looked like a brain but behaved like a junk drawer. Plenty of dots, most of them isolated islands touching nothing, and the documents I actually needed I was finding through global search, not the graph. Between the slogan — “turn your documents into a neural network” — and what I actually held in my hands, there was a clear gap.
2026-06-16
Quantum Computers Won't Crack Your Encrypted Database
“Once quantum computers arrive, won’t your database encryption solution be useless too?” When you tell people you build security products, this is the question you hear most often these days. A vague dread sits behind it. The moment the word quantum shows up, an apocalyptic image follows — every lock in the world springing open at once. There is one decisive misconception buried in that fear: it treats “encryption” as a single block. In reality, encryption splits into two camps with entirely different characters, and a quantum computer topples only one of them. The side that falls is not the encryption that locks data itself, but the encryption that establishes trust when data is exchanged. Fail to draw that line, and you will forever misjudge the size of the threat.
2026-06-13
Fable 5: Warp Drive, or Marketing Mirage?
I ran Claude Code with Fable 5 and requested security analysis across several rounds, hoping to verify the ‘Mythos-class’ security performance Anthropic has been touting. The result was a letdown. The analysis kept getting bounced back to Opus 4.8, and on the rare run where Fable 5 carried the work through to the end, the output never stepped an inch beyond the ground Opus had already covered. When the Guardrail Blocks the Defender Anthropic’s line is that it blocks abuse by attackers while permitting requests from defenders. In practice, though, Fable 5 kept rerouting even defensive vulnerability-analysis requests to Opus. My attempt to outpace attackers with a top-tier agent was braked, again and again, by the conservative guardrail the model imposes on itself. Can we really call it ‘safety’ when the security tool ties the defender’s hands?
2026-06-11
The Agent's Warp Drive, and the Omens of a Widening Divide
The hottest topic in the tech scene over the last day or two is, without question, Claude Fable 5 (formerly Mythos). Anthropic unveiled Fable 5, opening the first act of a ‘Mythos-class’ that surpasses Opus. This is not merely news that a benchmark number went up. This morning, hooking Fable 5 into Claude Code and putting it to real work left me closer to bewilderment than wonder. Even on the $200/mo Max plan, the agent is subject to strict token quotas on a 5-hour and weekly basis — and Fable 5 drained that 5-hour allotment in just two hours. Compared with Opus, where filling a full five hours still spent only around 30% of the limit, the token consumption is overwhelming.
2026-06-10
Putting MCP to Work Inside the Company
Lately I’ve been wiring MCP into our internal work, one piece at a time. Nothing as grand as standing up a platform — just enough to wrap a few internal services in MCP so the things I already do (handling issues, building and deploying, keeping docs in order) can be finished from inside Claude Code. After living with it for a while it stuck better than I expected, so here’s a light writeup of how it went.
2026-06-06
How MCP Became the Standard
In the previous post I argued that an MCP server is just an adapter with no intelligence of its own. Once you frame it that way, a new question appears. There are countless ways to build a dumb adapter that wraps some service’s API. So why did this one convention, MCP, take the seat of the standard that connects LLMs to tools? The answer is not some flashy feature. It is in how the protocol was designed.
2026-06-04