this post was submitted on 10 Jun 2026
1536 points (99.4% liked)

Technology

85333 readers
4415 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
you are viewing a single comment's thread
view the rest of the comments
[–] stickyprimer@lemmy.world 26 points 22 hours ago (4 children)

91% accuracy is the kind of thing that may sound good… hey! It’s an A minus! But it’s actually completely, totally unacceptable. Imagine if the turn signal wand on your car operated with 91% accuracy. About one in every ten times it would light up the wrong direction. How many accidents are we causing? A lot.

[–] mabeledo@lemmy.world 2 points 1 hour ago

Even the number is a bit misleading. First of all, anyone who has ever done LLM benchmarking knows that this isn’t an exact science, at all. You can totally get a 99% on a benchmark and fail every single task on another.

But even this particular claim is nuanced. From the original article:

But with Gemini 3, Google’s A.I.-generated answers were more likely to be ungrounded than when the system was based on Gemini 2, meaning the websites they linked to did not completely support the information they provided. In October, correct answers were ungrounded 37 percent of the time. In February, with Gemini 3, that figure rose to 56 percent.

See https://www.nytimes.com/2026/04/07/technology/google-ai-overviews-accuracy.html

Meaning that 56% of the time, users cannot even verify the information given by the LLM with the sources the LLM claims it’s using.

[–] Impractical_Island@lemmy.world -3 points 19 hours ago (1 children)

This is why we should ban cars outright. Go back to writing on paper. I can stick a pen in my ass and make a cute drawing of a cat. In fact, I might be able to eat a cat and defecate it later, to make it more realistic. And that's what we need to be; realistic.

(This comment is about AI data centers)

[–] Impractical_Island@lemmy.world -2 points 19 hours ago (1 children)

I make this "comment" every once and a while because I called someone out on how their post made little sense by parodying it, and now I just do this.

[–] stickyprimer@lemmy.world 5 points 10 hours ago (1 children)

I’m glad you’re entertaining yourself because I have no idea what you’re prattling about.

[–] Impractical_Island@lemmy.world 1 points 1 hour ago* (last edited 1 hour ago)

I'm drawing attention to my educational (f)art project while simultaneously goading someone who thought a less-hyperbolous but still nonsensical analogy was the greatest tweet anyone's ever made. I mean, I remember the first time something I did got seen by millions, so I can understand their enthusiasm to defend it, at the same time, we're still talking about AI data centers, right? I am, at least.

[–] LovableSidekick@lemmy.world 0 points 19 hours ago* (last edited 19 hours ago) (1 children)

Whether 91% accuracy is acceptable depends on how unacceptable the 9% inaccuracy is. If 91% of the information in your term paper is correct you'll probably get a decent grade, but if you only kill 91% of cancer cells the surviving 9% will grow a treatment-resistant tumor and you'll probably die. This makes percentages essentially useless - more important is how badly wrong the worst wrong result is.

[–] stickyprimer@lemmy.world 2 points 10 hours ago

So whether it’s acceptable depends on whether it’s acceptable. I agree!