0
Prompting is the Problem (?)
April 22, 2026
Posted 2 hours ago by
Apostolos Koutropoulos, Multilitteratus Incognitus, Apr 22, 2026 Apostolos Koutropoulos responds to an article in TD magazine (both link and archive link point to a paywall, so don't bother). He writes, There are two threads here. In one thread, I feel like the author is trying to get a bit Vygotskian here and treating the LLM like a more knowledgeable other, which they are not...
The other thread is that the LLM becomes a mirror for your thoughts. Cool, I guess, but do we really need a modern-day ELIZA. But the main complaint is that it seems to treat the failings of the LLM as the fault of the user. Now granted, LLMs are not perfect. That doesn't mean they should be written off completely. They do some things very well. And to that extent, the skill of the user does come into play, if only to use them for tasks where they excel, and not where they don't. Web: [Direct Link] [This Post]
Stephen's Web ~ OLDaily
Coverage and analysis from Canada. All insights are generated by our AI narrative analysis engine.