this post was submitted on 04 Apr 2025
351 points (88.1% liked)

Technology

68349 readers
4627 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 2 years ago
MODERATORS
top 50 comments
sorted by: hot top controversial new old
[–] ICastFist@programming.dev 4 points 1 hour ago

Anthropic made lots of intriguing discoveries using this approach, not least of which is why LLMs are so terrible at basic mathematics. "Ask Claude to add 36 and 59 and the model will go through a series of odd steps, including first adding a selection of approximate values (add 40ish and 60ish, add 57ish and 36ish). Towards the end of its process, it comes up with the value 92ish. Meanwhile, another sequence of steps focuses on the last digits, 6 and 9, and determines that the answer must end in a 5. Putting that together with 92ish gives the correct answer of 95," the MIT article explains.

But here's the really funky bit. If you ask Claude how it got the correct answer of 95, it will apparently tell you, "I added the ones (6+9=15), carried the 1, then added the 10s (3+5+1=9), resulting in 95." But that actually only reflects common answers in its training data as to how the sum might be completed, as opposed to what it actually did.

Another very surprising outcome of the research is the discovery that these LLMs do not, as is widely assumed, operate by merely predicting the next word. By tracing how Claude generated rhyming couplets, Anthropic found that it chose the rhyming word at the end of verses first, then filled in the rest of the line.

[–] Technoworcester@lemm.ee 140 points 1 day ago (2 children)

'is weirder than you thought '

I am as likely to click a link with that line as much as if it had

'this one weird trick' or 'side hussle'.

I would really like it if headlines treated us like adults and got rid of click baity lines.

[–] BackgrndNoize@lemmy.world 38 points 23 hours ago (1 children)

But then you wouldn't need to click on thir Ad infested shite website where 1-2 paragraphs worth of actual information is stretched into a giant essay so that they can show you more Ads the longer you scroll

[–] Technoworcester@lemm.ee 22 points 19 hours ago (2 children)

I will never understand how ppl survive without ad blockers. Tried it once recently and it was a horrific experience.

[–] BackgrndNoize@lemmy.world 6 points 18 hours ago

I'm thankful for such people's sacrifice, if it wasn't for them there would be even more anti ad block measures in place

[–] electric@lemmy.world 1 points 13 hours ago (1 children)

Same way you survive live TV. You learn to mentally block out ads.

[–] Burninator05@lemmy.world 5 points 13 hours ago (1 children)
[–] electric@lemmy.world 2 points 12 hours ago

Not anymore, of course. But nothing beats that brain rot apart from sites that hijack your controls.

[–] BeardedGingerWonder@feddit.uk 15 points 1 day ago (4 children)

They do it because it works on the whole. If straight titles were as effective they'd be used instead.

[–] EpeeGnome@lemm.ee 2 points 15 hours ago (1 children)

Well, I'm doing my part against them by refusing to click on any bait headlines, but I fear it's a lost cause anyway.

[–] BeardedGingerWonder@feddit.uk 5 points 14 hours ago

I try and just ignore it and read what I'm interested in regardless. From what I hear about the YouTube algo, for instance, clickbait titles are necessity more than a choice for YouTubers, if they don't use them they get next to no engagement early and the algo buries that video which can impact the channel in general.

load more comments (3 replies)
[–] cholesterol@lemmy.world 37 points 1 day ago (1 children)

you can't trust its explanations as to what it has just done.

I might have had a lucky guess, but this was basically my assumption. You can't ask LLMs how they work and get an answer coming from an internal understanding of themselves, because they have no 'internal' experience.

Unless you make a scanner like the one in the study, non-verbal processing is as much of a black box to their 'output voice' as it is to us.

[–] cley_faye@lemmy.world 4 points 14 hours ago

Anyone that used them for even a limited amount of time will tell you that the thing can give you a correct, detailed explanation on how to do a thing, and provide a broken result. And vice versa. Looking into it by asking more have zero chance of being useful.

[–] SplashJackson@lemmy.ca 5 points 17 hours ago (1 children)
[–] nilclass@discuss.tchncs.de 4 points 17 hours ago

You can become one too! Get your certification here https://mt.cert.ccc.de/

[–] dkc@lemmy.world 49 points 1 day ago (1 children)

The research paper looks well written but I couldn’t find any information on if this paper is going to be published in a reputable journal and peer reviewed. I have little faith in private businesses who profit from AI providing an unbiased view of how AI works. I think the first question I’d like answered is did Anthropic’s marketing department review the paper and did they offer any corrections or feedback? We’ve all heard the stories about the tobacco industry paying for papers to be written about the benefits of smoking and refuting health concerns.

[–] StructuredPair@lemmy.world 13 points 19 hours ago

A lot of ai research isn't published in journals but either posted to a corporate website or put up on the arxiv. There are some ai journals, but the ai community doesn't particularly value those journals (and threw a bit of a fit when they came out). This article is mostly marketing and doesn't show anything that should surprise anyone familiar with how neural networks work generically in my opinion.

[–] shaggyb@lemmy.world 8 points 1 day ago

Don't tell me that my thoughts aren't weird enough.

[–] perestroika@lemm.ee 10 points 1 day ago* (last edited 1 day ago) (1 children)

Wow, interesting. :)

Not unexpectedly, the LLM failed to explain its own thought process correctly.

[–] shneancy@lemmy.world 2 points 5 hours ago

tbf, how do you know what to say and when? or what 2+2 is?

you learnt it? well so did AI

i'm not an AI nut or anything, but we can barely comprehend our own internal processes, it'd be concerning if a thing humanity created was better at it than us lol

load more comments