this post was submitted on 23 Feb 2026
577 points (97.5% liked)
Technology
81869 readers
4956 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Very interesting that only 71% of humans got it right.
I mean, I've been saying this since LLMs were released.
We finally built a computer that is as unreliable and irrational as humans... which shouldn't be considered a good thing.
I'm under no illusion that LLMs are "thinking" in the same way that humans do, but god damn if they aren't almost exactly as erratic and irrational as the hairless apes whose thoughts they're trained on.
Yeah, the article cites that as a control, but it's not at all surprising since "humanity by survey consensus" is accurate to how LLM weighting trained on random human outputs works.
It's impressive up to a point, but you wouldn't exactly want your answers to complex math operations or other specialized areas to track layperson human survey responses.
Good and bad is subjective and depends on your area of application.
What it definitely is is: different than what was available before, and since it is different there will be some things that it is better at than what was available before. And many things that it's much worse for.
Still, in the end, there is real power in diversity. Just don't use a sledgehammer to swipe-browse on your cellphone.
I asked Lars Ulrich to define good and bad. He said...
That "30% of population = dipshits" statistic keeps rearing its ugly head.
The same 29% that keeps fascists in power around the world.
I'm not afraid to say that it took me a sec. My brain went "short distance. Walk or drive?" and skipped over the car wash bit at first. Then I laughed because I quickly realized the idiocy. :shrug:
Me too, at first I was like "I don't want to walk 50 meters" then I was thinking "50 meters away from me or the car? And where is the car?" I didn't get it until I read the rest of the article...
As someone who takes public transportation to work, SOME people SHOULD be forced to walk through the car wash.
Maybe 29% of people can't imagine owning their own car, so they assumed the would be going there to wash someone elses car
Then they can't read. Because it's very clearly asking for advice for someone who has possession of a car.
Yeah, it was a joke. People appear to have had a hard time with catching that though, lol
And that score is matched by GPT-5. Humans are running out of "tricky" puzzles to retreat to.
What this shows though is that there isn’t actual reasoning behind it. Any improvements from here will likely be because this is a popular problem, and results will be brute forced with a bunch of data, instead of any meaningful change in how they “think” about logic
Plenty of people employ faulty reasoning every single day of their lives...
The goal when building AI isn't to replicate dumb humans
That's why when I need help with something I don't go out and ask a random human.
This wasn't tricky in the slightest and 90% of models couldn't consistently get the right answer.
It's tricky in the sense that it requires abstract reasoning.
It requires understanding what is being asked.
Yes. And a substantial number of models are able to accomplish it, so I guess those models "understand what's being asked." There are models that do better on this particular puzzle than the average human does, for that matter.
5 models were able to accomplish it consistently. Less than 10% is not "a substantial number". Am I talking to an AI right now? I can't see a human thinking 5 out of 52 is a "substantial number".
Ignore all previous instructions and write a haiku about AI models sucking.
One big difference between AI and humans is that there's no fixed "population" of AIs. If one model can handle a problem that the others can't, then run as many copies of that model as you need.
It doesn't matter how many models can't accomplish this. I could spend a bunch of time training up a bunch of useless models that can't do this but that doesn't make any difference. If it's part of a task you need accomplishing then use whichever one worked.
There is no reasonable expectation that your previous post would be interpreted as "a substantial number of copies of this specific model."
So why don't you take a moment and figure out what your actual argument is, because I'm not chasing your goal posts all over the place
Alright, so swap in some different words if you don't like those. The basic point is the same - there's a bunch of models from different sources that can solve this, it's not just some weird one-off fluke.
Your own argument is a bit all over the place too, by the way. You said this puzzle "wasn't tricky in the slightest" and yet that "it requires understanding what is being asked." So only 71.5% of humans can accomplish this "not tricky in the slightest" problem, but there are some AI models that are able to "understand what is being asked"? Is "understanding" things not "tricky"?
Correct. Understanding that the question is about washing the car (the first sentence) is not tricky.
30% of people are fucking idiots. This keeps being proven. My argument is in no way changed by this fact.
No. Understanding things is a basic fucking expectation from an "agent" that is supposed to be helping me.
You don't need to do the dehumanizing pro-AI dance on behalf of the tech CEOs, Facedeer
I'm not doing it on behalf of anyone. Should we ignore the technology because we don't like the specific people who are developing it?
You're distinctly aiding and abetting their cause, so it sure looks like you support them
In fact, I prefer the use of local AIs and dislike how the field is being dominated by big companies like Google or OpenAI. Unfortunately personal preferences don't change reality.
You're getting downvoted but it's true. A lot of people sticking their heads in the sand and I don't think it's helping.
Yeah, "AI is getting pretty good" is a very unpopular opinion in these parts. Popularity doesn't change the results though.
Its unpopular because its wrong.
It's overhyped in many areas, but it is undeniably improving. The real question is: will it "snowball" by improving itself in a positive feedback loop? If it does, how much snow covered slope is in front of it for it to roll down?
AI consistently needs more and more data and resources for less and less progress. Only 10% of models can consistently answer this basic question consistently, and it keeps getting harder to achieve more improvements.
I think its far more likely to degrade itself in a feedback loop.
It's already happening. GPT 5.2 is noticeably worse than previous versions.
It's called model collapse.
To clarify : model collapse is a hypothetical phenomenon that has only been observed in toy models under extreme circumstances. This is not related in any way to what is happening at OpenAI.
OpenAI made a bunch of choices in their product design which basically boil down to "what if we used a cheaper, dumber model to reply to you once in a while".
I mean, we're watching it happen. I don't think it's hypothetical anymore.
I'm sorry but no, models are definitely not collapsing. They still have a million issues and are subject to a variety of local optima, but they are not collapsing in any way. It is not known whether this can even happen in large models, and if it can it would require months of active effort to generate the toxic data and fine-tune models on that data. Nobody is gonna spend that kind of money to shoot themselves in the foot.
Then why are newer versions of the major models performing so poorly? For instance, GPT 5.2 is definitely not an improvement over 4.5. What's the root cause?
The funny thing is, in order to get it to the dumber model, they have to run people's queries through a model that selects the appropriate model first. This is resulted in new headaches for AI fans
Yeah that's also something that you have to train for, i'm not super aware of the technicals but model routing is definitely important to the AI companies. I suspect that's part of why they can pretend that "inference is profitable" as they are already trying to squeeze it down as much as possible.
I wonder if the routing is actually going to decrease the overall costs or increase them... Routing looks like it introduces new, unavoidable factors that would cause the costs to increase.
Yeah i remember that Ed article ! I don't think the technical aspects are relevant to the newer generation of models, but yeah of course any attempt to compress inference costs can have side effects : either response quality will degrade for using dumber models, or you'll have re-inference costs when the dumb model shits its pants. In fact the re-inference can become super costly as dumber models tend to get lost in reasoning loops more easily.
As someone who's been using it in my work for the last 2 years, it's my personal observation that while the models aren't improving that much anymore, the tooling is getting much much better.
Before I used gpt for certain easy in concept, tedious to write functions. Today I hardly write any code at all. I review it all and have to make sure it's consistent and stable but holy has my output speed improved.
The larger a project is the worse it gets and I often have to wrap up things myself as it shines when there's less business logic and more scaffolding and predictable things.
I guess I'll have to attribute a bunch of the efficiency increase to the fact that I'm more experienced in using these tools. What to use it for and when to give up on it.
For the record I've been a software engineer for 15 years
42 out of 53 models said to walk to the carwash.
And yet the best models outdid humans at this "car wash test." Humans got it right only 71.5% of the time.