Post #2769030

2026-03-18 14:41 UTC

@happyborg@fosstodon.org @kornel@mastodon.social Very much agreed! Aside from natural language not being adequate enough to specify requirements clearly, we as humans are notoriously bad at describing things we want, let alone *need*. If we remove human interaction from the whole process, I'm afraid we also lose a large chunk of critical thinking in the sense of "should we actually do this?". LLMs can't do that critical thinking part for us.

Replies (2)

@kornel@mastodon.social 2026-03-18 14:52

@iainvdw@mastodon.social @happyborg@fosstodon.org Currently we think before writing code, because writing it and changing it takes effort (and even for LLM-generated slop code it takes time, and burns money and rainforests, so it's better to get the spec right first) But the thing I've been wondering about is that if generation speed improves significantly, it will change the problem from "should we write it like this?" to "I've written it. Is this what you wanted? How about this? Or that? Here's 10 more with benchmarks"

Open ##2769031
@happyborg@fosstodon.org 2026-03-18 14:58

@iainvdw@mastodon.social yes indeed, I confess to oversimplifying - one could write a book - but it is necessary in this format and to have a decent chance of being understood by people who IMO don't seem to understand what software engineering requires, even if they are smart and have been programming for a long time. My belief is that it requires perspicacity, and a willingness to question and critique that many, including programmers lack. @kornel@mastodon.social

Open ##2769034