> "The IDE, on Visual FoxPro's own sample projects. Every picture is a real session." starting to have involuntary revulsive twitches from Claude prose
Despite what the marketing material would have you believe you can always see the fold. Even when it's fully open. Folding screens have been a solution in search of problem for like a decade now
Relying on CoT (and, similarly, asking the model to explain its actions) for analysis has always seemed pretty silly (naive?) to me, but maybe I'm missing something. Why do are we so committed to preserving it? And do non-textual models provide some similar form of tracing?
reply