Very interesting that only 71% of humans got it right.
this post was submitted on 23 Feb 2026
1 points (100.0% liked)
Technology
82227 readers
4334 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
And that score is matched by GPT-5. Humans are running out of "tricky" puzzles to retreat to.
Humans are running out of "tricky" puzzles to retreat to.
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.
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".
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.
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?
Maybe 29% of people can't imagine owning their own car, so they assumed the would be going there to wash someone elses car