712
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 23 Feb 2026
712 points (100.0% liked)
Technology
84041 readers
3031 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
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.
As someone who takes public transportation to work, SOME people SHOULD be forced to walk through the car wash.
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...
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
Are you sure?
That's why when I need help with something I don't go out and ask a random human.
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?
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".
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 feel that a lot of what is improving in the recent batch of model releases is the vetting of their training data - basically the opposite of model collapse.
Nothing requires an LLM to train on the entire internet.
That's an excellent point! On that topic I recently listened to an interview of the founder of EleutherAI, who focuses on training small language models. She said they were able to train a 1B parameters reasoning model with 50K Wikipedia articles and carefully curated RL traces. The thing could run in your smartphone and is at parity with much larger models trained on trillions of tokens.
She also scoffed at Common Crawl and said it contained mostly cookies and porn. She had a kind of attitude like "no wonder the big labs need to slurp trillions of tokens when the tokens are such low quality". Very interesting approach, if you understand french I can only recommend the interview.
The very interesting part will be how successful they are at training the training data selectors to choose high quality data sources.
I think a lot of it is still done by hand, and there is also synthetic data distilled from larger models of course.
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.
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.
You don't need to do the dehumanizing pro-AI dance on behalf of the tech CEOs, Facedeer
This wasn't tricky in the slightest and 90% of models couldn't consistently get the right answer.
The same 29% that keeps fascists in power around the world.
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