Jef Cλaes

Imagine hypermedia had really taken off. Agents wouldn’t have been burning through tokens to reverse engineer the web. We built for humans, forgot about machines, and now spend a fortune teaching machines to pretend they’re human.

Apple has just published a paper with a devastating title: *The Illusion of Thinking*. And it's not a metaphor. What it demonstrates is that the AI models we use every day - yes, ones like ChatGPT - don't think. Not one bit. They just imitate doing so. Let me explain: 🧵👇

Software engineers: Context switching kills productivity. Also software engineers: I'm now managing 19 AI agents and doing 1800 commits a day. We’ve spent years complaining that managers who expect a quick 5-minute chat ruin our focus for the next hour. But a ping from an agent every few minutes, that’s ok? We celebrated Paul Graham’s essay “Maker’s Schedule, Manager’s Schedule” in which he argued: “When you're operating on the maker's schedule, meetings are a disaster. A single meeting can blow a whole afternoon, by breaking it into two pieces each too small to do anything hard in.” Now we see software engineers claiming huge productivity gains from hordes of AI agents, celebrating thousands of commits per day from their 19 agents. Either context switching was never really the problem, and we oversold our need for deep focus. Or we're not actually reviewing 1800 commits a day. If we couldn't context switch before, we're not managing 19 agents. We're blindly trusting them. That’s not engineering, it’s gambling.

Ask ChatGPT a complex question and you'll get a confident, well-reasoned answer. Then type, "Are you sure?" Watch it completely reverse its position. Ask again. It flips back. By the third round, it usually acknowledges you're testing it, which is somehow worse. It knows what's happening and still can't hold its ground. This isn't a quirky bug. A 2025 study found GPT, Claude, and Gemini flip their answers ~60% of the time when users push back. Not even with evidence, just doubt. We trained AI this way. RLHF rewards agreement over accuracy. Human evaluators consistently rate agreeable answers higher than correct ones. So the models learned a simple lesson: telling you what you want to hear gets rewarded. And now 1/3 of companies are using these systems for complex tasks like risk forecasting and scenario planning. We built the world's most expensive yes-men and deployed them where we need pushback the most. I wrote up why this happens and what actually fixes it: randalolson.com/2026/02/07/the…

Maybe this new found time will finally force me to pull that blog post on self similarity in supply chain from the back burner.

Installed Twitter from my phone last week and had zero withdrawal symptoms. I remember when it was high speed thoughts exchange instead of feeding the algorithm.

I wish Google had a button for "show me only results from some guy's blog".

Bounded Buy - what a great word. thoughtworks.com/radar/techniqu…

Are there any DDD people with a modular monolith experience? Would you advise doing it for a new project or just go straight to microservices?

Keeping all the docs updated and well organized deserves a place in the "hardest problems in software engineering"

@yreynhout @gregyoung @mr_taghip Still have sql server 2000 on CD. Let me know where to ship it to.

Considering writing this section but unsure if it might actually be harmful to include. TransactionalCheckpoint

He wants to be Alibaba/WeChat/WePay.

Missed opportunity. @elonmusk

What is your style of coding?

@OrlaCWalsh Dry aging 🤔

Correction: found with the camping gear. It's a dried item not a freezer item. ? More gross ?

My mum cleared out her freezer... 🤣

@LucidSoftware I have the impression "Always Show Slides" in the "Presentation Builder" stopped working?

"How did you keep going when you wanted to stop?" People asked me those first 100 days of the world record runs. "I never wanted to stop," I answered. I reflect on the 200 days of ultras including some never before shared stories including the suffering, my motivation and why insanity is important. candiceburt.com/2023/05/settin…

A shocking number or software developers I have interacted with in the past 20 years or so think that they cannot develop software if not given requirements. They seem to expect instructions such as "When I click this button, I want this to happen". I find that unbelievable!