That's an excellent idea I plan to try, thanks—re using structured JSON with schema. The most success I've had is saying "be brief" or an explicit size, like one line, or do not explain, etc. I haven't measured other instructions so extensively. They do work but the more specific the better. Other strategies around outputs that are more natural language seem to be hands-down the direction to take, and get away from the machine language habits we've used in the past. It's super interesting seeing this new practice emerging and more or less inventing parts of it along the way. Right now I'm at the place where my brute force and elaborate explanations were reaching their limit and in the frustration just realized I need to take a few days and try to figure out the tool. Across all these the pattern seems entirely that the constraints bound the probability space, whether it's the format like you suggested, or the instruction we give, including the space we point it toward (Web APIs, runtime, schema, etc). In all instances where it's not working the solution seems to be what does the pattern reduce to, and what specifics are the do/don't to go with that, and most of the time the results improve immediately. Your tip seems excellent for this. An easy-button.
Reviewing my experience using LLMs, to improve results, reduce churn and token usage. Discovering the gap between what they produce and what I'd normally do is a significant source of output cost, regressions and surfacing a bit of why and how to fix it. Notably Claude is remarkably bad at/about this, producing errors even when directed toward modern Web solutions—that cut token use a lot, like toward 90% occasionally, which together with the frustrating churn led me to review how I'm working, what is happening and generate this article.
Turn off the ability to add hyperlinks and use words instead? Is that what comments were intended for anyway? Seems a bit convoluted, but limiting comments, to comments, would be fairly natural. It'll get subverted anyway, but likely affects. A policy could say don't use hyperlinks, feel free to say where to go. Which would be an interesting policy to technically enforce, and still have the discretion to operate on.
Organizations are choosing to eliminate workers rather than amplify them with AI because they'd rather own 100% of diminished capacity than share proceeds from exponentially increased capacity. That's the rent extraction model consuming its own productive infrastructure.
The Stanford study documents organizations systematically choosing inferior economic strategies because their rent-extraction frameworks cannot conceptualize workers as productive assets to amplify.
This reveals that these organizations are economic rent-seekers that happen to have productive workers, not production companies that happen to extract rents. When forced to choose between preserving rent extraction structures or maximizing value creation, they preserve extraction even at the cost of destroying productive capacity. So what comes next?