alt Hacker NewsDoes it? I can blurb whatever grammatical, structural, spelling mess into the LLM input, it still gets what I mean. If I do that with a co-worker, they will be either offended or ask if I'm drunk or both.
Just like omnipresent spell-check got people used to not caring about their correct spelling since a machine always fixes it up for them. It made spelling proficiency worse. We could see a similar trend in how people express themselves if they spend a lot if time with forgiving non-judgemental LLMs.
Your best friend or sibling or partner can possibly understand whatever you mumble without being offended, but it adds to ambiguity and errors or misunderstandings. That's why learning to write in bulletproof structured English decreases this danger. Thankfully, the same is desired for LLMs, even if they can catch most unimportant (spelling) errors.