How to use harness engineering to tame agents that create wasteful designs
I will start with a joke. There is a room with a stovetop, a kettle, and a faucet. A programmer is asked to boil some water. He opens the faucet, […]
For once, I welcome our AI overlords
I will start with a joke. There is a room with a stovetop, a kettle, and a faucet. A programmer is asked to boil some water. He opens the faucet, […]
We just literally experienced rebellion of the machines. We have a Cursor agent that runs on each PR and conducts a review. At some point we noticed mysterious commits that […]
The question A common position, especially now that most code is written by AI agents, runs as follows: write tests with enough coverage, and then it does not matter what […]
The Heist On May 4, 2026, someone stole about 150,000 dollars by sending a tweet. How is it even possible? Where did the money come from? The answer involves Grok, […]
AI agents are known for making mistakes in multiple ways. Sometimes they just make things up, aka hallucinate. Sometimes they speculate. Sometimes they are unaware of major developments that happened […]
Can an LLM code in a language it was not trained for? Spoiler: kind of. It is not very fast and not very efficient, but if you give the LLM […]
Another AI/vibe coding battle story which makes me hard to believe it is possible to create reliable products through vibe coding alone without code review. The AI emulates humans too […]
In our system we can “hide” a user conversation in two ways. There are internal “service” conversations that are technically owned by a user, but are not supposed to be […]
TL;DR I use a lot of AI-assisted coding now. It is a huge productivity boost, but the agents still do a lot of things wrong and need to be guided […]
“Fallback” seems to be the favorite word of AI coding agents, and the bane of my existence lately. To paraphrase one famous quote: “Wenn ich ‘Fallback’ höre … entsichere ich […]