this post was submitted on 24 Jun 2026
130 points (95.8% liked)

Technology

85670 readers
3977 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. 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.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 3 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
130
Advanced AI models suffer a near-total collapse on classic psychology test as cognitive demands increase (www.psypost.org)
submitted 13 hours ago by sanitation@lemmy.today to c/technology@lemmy.world
26 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] ryannathans@aussie.zone 1 points 11 hours ago (2 children)

These models tested are so old they're from the era where they couldn't pass a math test or count letters in words

[–] scratchee@feddit.uk 2 points 2 hours ago* (last edited 2 hours ago) (1 children)

Afaik that is handled through tool use in modern models (ie they didn’t learn to do maths, they learnt to use a calculator), assuming that’s true and I haven’t missed some advance, their conclusions are likely still relevant

Edit: though the article does seem to discard the chain of thought techniques a little readily, feels like they could come close to fitting the role of executive control, but perhaps that’s just the article lacking detail from the original work.

[–] Monument@piefed.world 2 points 1 hour ago (1 children)

My high school math teachers would be so disappointed in them.

[–] scratchee@feddit.uk 2 points 1 hour ago

If I could wire a calculator into my brain I would have cheated on all the maths tests tbf

[–] khornechips@sh.itjust.works 10 points 8 hours ago (1 children)

So… last week then?

[–] communist@lemmy.frozeninferno.xyz -3 points 5 hours ago (2 children)

I get that you hate AI but there's no reason to lie about its capabilities.

[–] criss_cross@lemmy.world 3 points 2 hours ago

A lot of tools like Claude or ChatGPT have internal tools they call when they do math (or use a python script) rather than have the model actually compute anything.

The underlying tech itself can’t do it because you can’t do math by token probability.

[–] expr@programming.dev 8 points 4 hours ago

That's not lying. There's nothing linguistic about numerical computation.