if you're on free tier, using Medium settings is far more intelligent than Max, and tokens don't run out so fast. Max is cranky and verbose, Medium is patient and somewhat goofy, but does the thing as expected. At least within Sept 2026 this has been my experience.
The problem is particularly serious in some countries, like South Korea.
A recent popular Korean tv serial "teach you a lesson" became wildly popular despite being not-so-politically-correct, precisely because of the severity of the problem.
Wild how much of the successful entertainment coming out of South Korea (like Squid Game), is basically them dramatizing facets of their dystopian society, that a lot of it is actually based on real issues they face, and it's not all just made up fantasy.
Indeed. I haven't been to Korea but when I was in China, I met many Koreans and when I was taking Chinese lessons, some Koreans were in my class.
They are generally less friendlier than all the other foreigners I met, closed to outsiders, and somewhat racist (I asked a group of Koreans if I could join their game of Basketball, but they said they preferred to play by themselves. No Chinese ever said anything like that, nor any other foreigners I had joined to play with).
Also, they are quite a violent people. My classmates and I nearly came to blows over the window in the class; I wanted to open it because the indoor air was stale and probably toxic, but he didn't want the window open (for whatever reason, though the weather wasn't cold). Another non-Asian foreigner got into a fight with a Korean puncturing his eardrum which resulted in deafness. Outside the university, too, when they get drunk they become aggressive and seek fights. I guess it must be all the stress they're to put up with in their Dystopian country?
That's very sweet! But I recommend subscribing to me only once, not every time I write a comment. Otherwise you'll end up with thousands of duplicate subscriptions.
Yep, if I am interested or even obsessed by the text. I have read literature classics voraciously and have read books in one go in the past. I probably read some 50 books for my Masters. But unfortunately some documentation of a template language I need for a project, but am otherwise less interested in, fails to adequately fascinate me. Reading aloud helps me to concentrate on the boring text and actually read it, not skim without really understanding.
Point is, it is just one reading tool in the bag and it is foolish to think it has something to do with reading level or comprehension. Might be helpful for many people whose focus has been nuked by platform apps.
My six-year-old is probably a bit ADHD, and with parents like his it's not surprising, but he will sit and read for *hours*, and stuff that's way beyond what you'd expect of a six-year-old. It's about the only time he's really quiet, and I mean the good kind of quiet, not the "sudden transient to quiet" that means you must drop everything and RUN to find out what they're doing *now*.
instead of letting you search for info, now google is FEEDING you (often the wrong) info. I use Yandex, because that one still behaves like a search engine.
The reality is the Asian countries don't really think along the same lines as European-Americans. To an Asian, you will ALWAYS be an outsider, no matter what.
For the last four years, this is what LLMs have been doing as modus operandi:
1. here's thing you asked for. And here's a lot more you didn't ask for.
Then I notice there are mistakes, so I point them out. And I get this pattern:
2. Oh yes, sorry for that and thanks for pointing out my mistake. I think a better thing to do that would have been XYZ.
Then I see that the output is far from what I originally had in mind. I steer the LLM back by saying they have strayed and made the thing far more complicated than it should have been. And then I get this pattern of responses:
3. Oh right, you are right, I unnecessarily complicated it. Let me tackle it differently, simply just as you said I should.
By then I have run out of tokens, so I have to wait. When I have tokens again, I restart the convo, and once I get my 'solution', I notice that the LLM has done additional things in there that make it clear, at a glance, it was done by AI. I don't mind that so much as these create clutter and are totally unnecessary. So I ask it to clean it up and remove all those frills I never asked for. Then I get:
4. Got it, getting rid of those extra things.
Now the outcome I have is still a far cry from what I originally had intended to have. I would have been more efficient but definitely happier had I hand-coded it all by myself in the first place. It's not like I have to type everything out anyway, good IDEs already have made me fast.
There, now don't worry about AI taking your job. They can't and they won't.
PS. Pro-AI midwits will downvote this (it's a pattern on HN when you say sth against AI you get downvoted, so if you think I am right, please upvote so as to counter those midwit downvotes. It's a shame one has to change one's opinions in order for the opinion to be available to read. But I won't. I will say what I think, regardless of the downvotes).
if you're on free tier, using Medium settings is far more intelligent than Max, and tokens don't run out so fast. Max is cranky and verbose, Medium is patient and somewhat goofy, but does the thing as expected. At least within Sept 2026 this has been my experience.
reply