I've been thinking a bit about under what conditions humans need to understand the systems they're building. Chatted with GPT-6.1 Sol high, and I thought we reached a good argument for the human-AI collaboration to get better results. www.geoffreylitt.com/2026/07/02/...
Post
geoffreylitt.comUnderstanding is the new bottleneckAgents can write code faster than we can absorb it. Here's why it still matters for humans to understand what they build — and some techniques for doing that efficiently: explainer docs, quizzes, micro-worlds, and shared spaces.
Strangely, it said, it couldn't know the counterfactual of whether it could have come up with a better argument. But we can! I forked the convo, and rewound it back to the start, but then told GPT-6-astra max to argue with itself, consult w/ Opus 5.5 for another opinion, to see what it came up with.
Not to say that this can't be trained. But, for now and the foreseeable future, this and other exps make me think there's always going to be niches and blind spots the labs have. And even if they cover it, they might regress later. There's likely still value to having humans along for the ride.
0 reposts0 likes
No replies yet.