The force-feeding of AI features on an unwilling public

I’ve observed the opposite—not enough people are leveraging AI, especially in government institutions. Critical time and taxpayer money are wasted on tasks that could be automated with state-of-the-art models. Instead of embracing efficiency, these organizations perpetuate inefficiency at public expense.

The same issue plagues many private companies. I’ve seen employees spend days drafting documents that a free tool like Mistral could generate in seconds, leaving them 30-60 minutes to review and refine. There's a lot of resistance from the public. They're probably thinking that their job will be saved if they refuse to adopt AI tools.

The irony is it’ll likely be the opposite.

> I’ve seen employees spend days drafting documents that a free tool like Mistral could generate in seconds, leaving them 30-60 minutes to review and refine.

What I have seen is employees spending days asking the model again and again to actually generate the document they need, and then submit it without reviewing it, only for a problem to explode a month later because no one noticed a glaring absurdity in the middle of the AI-polished garbage.

AI is the worst kind of liar: a bullshitter.

You're describing incompetence or laziness—I’ve encountered those kinds of people as well. But I’ve also seen others who are 2-3 times more productive thanks to AI. That said, I’m not suggesting AI should be used for every single task, especially if the output is garbage. If someone blindly relies on AI without adding any real value beyond typing prompts, then they’re not contributing anything meaningful.

Yeah, no you cant see that yet. What you see is comparison between own super optimistic imagined idea of useful AI with either reality or even knee jerk "goverment is stupid and wastful becauce Musk said so".

Days to write a document, but you think that it'll only take 30-60 minutes to review AI slop that may, or may not, bear any relationship to the truth?

The thing is, though, that time wasn’t wasted. It was spent fully understanding what they were actually trying to say, the context, the connotations of various different phrasings etc. It was spent mapping the territory. Throwing your initial, unexamined description into a prompt might generate something that looks enough like the email they’d have written, but it’s not been thought through. If the 10 minutes’ thought spent on the prompt was sufficient, the final email wouldn’t be taking days to do by hand.

I'm talking boilerplate, not scientific research. It's crazy that we're starting to see research done by AI but a lot of boilerplate is still done manually.

> incompetence or laziness [...] If someone blindly relies on AI

That's basic human behavior and AI won't fix this. It will only make it worse, and that's my main gripe with AI.