this post was submitted on 04 Jul 2025
32 points (60.5% liked)

Technology

72455 readers
3042 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
 

By 2030, AI will greatly outperform humans in some complex intellectual tasks. Discover how LLMs are doubling their capabilities every seven months.

top 50 comments
sorted by: hot top controversial new old
[–] [email protected] 2 points 1 day ago

they are improving at an exponential rate. It's just that the exponent is less than one.

[–] [email protected] 2 points 2 days ago

new moore law dropped

[–] [email protected] 15 points 2 days ago (1 children)

Someone doesn't know the folly of extending straight lines graphs into the future.

[–] [email protected] 8 points 2 days ago* (last edited 2 days ago) (1 children)
[–] [email protected] 2 points 2 days ago

Oof, the alt text on that second one was unexpectedly dark lmao

[–] [email protected] 12 points 2 days ago* (last edited 2 days ago) (1 children)

when will they be able to tell me how many 'r's are in 'strawberry' in under 1s?

[–] [email protected] 7 points 2 days ago (1 children)

Deepseek-r1:1.5b

Thinking

Thinking...
Alright, so I'm trying to figure out how many 'r's are in the word "strawberry." Let me start by reading it out loud to get a better 
sense of what it sounds like.

S-T-R-A-W-B-E-R-R-Y

Okay, let's break this down letter by letter. The first letter is S, then T, R, A, W, B, E, and two R's at the end.

So far, I've got one 'R' in the third position after S-T- and before A-W-B-E-R-R-Y.

Wait a minute, there are two R's in "strawberry." So that means there are two instances of the letter 'r' in the word. Is that all?

Let me double-check to make sure I'm not missing any other 'r's. Scanning through each letter again:

1. S - No
2. T - No
3. R - Yes, one R here.
4. A - No
5. W - No
6. B - No
7. E - No
8. R - Second R
9. R - Third R

Wait, am I counting correctly? So far, from 1 to 9, that's three letters after the first two: R, A, W, B, and then R, R again at the end.

Hold on, maybe I should visualize it like this:

S T R A W B E R R Y

So positions:
1. S
2. T
3. R (position 3)
4. A
5. W
6. B
7. E
8. R (position 8)
9. R (position 9)

And then the word ends with 'Y.'

Hmm, so only two 'R's in total? Let me confirm:

Looking back: positions 3 and 8 and 9.

Wait, that makes three 'R's. Did I miss one?

Hold on, maybe I need to write it out clearly to visualize better:

S T R A W B E R R Y

Counting each 'R':

- After S (position 2): No
- After T (position 3): Yes, first R
- After A (position 4): No
- After W (position 5): No
- After B (position 6): No
- After E (position 7): No
- After R (position 8): Second R
- After R (position 9): Third R
- After Y (position 10): No

So that's three 'R's in total. Did I count right? Maybe I should write it down step by step to ensure accuracy.

Alternatively, maybe there are only two 'R's because the 'Y' is considered separate from the R. But logically, even if Y has a vowel 
sound, 'r' still counts separately unless specified otherwise.

Wait, actually, in English letters, 'Y' isn't really pronounced like an 'R.' It sounds more like a consonant. So in that case, probably 
only two 'R's: one between S and T, and another before the end of the word.

But I'm still confused because when I count, I sometimes make mistakes. Maybe using an alphabet list or a counting tool would help.

Let me write down each letter with its position:

1. S
2. T
3. R (count 1)
4. A
5. W
6. B
7. E
8. R (count 2)
9. R (count 3)
10. Y

So that's three 'R's in total.

Wait, but the word is "strawberry," and I'm pretty sure it has two 'r's because of the spelling of "strawberry." Maybe the counting 
matches that.

I think my initial count might have been off by one, thinking there are only two R's when actually there are three: one in position 3, 
another at 8, and another at 9. But given that Y isn't pronounced like an 'R,' it's more accurate to say there are two 'r's.

Hmm, maybe I need to consider the pronunciation of each letter as well. Even though 'Y' is a consonant, sometimes people might play 
around with silent letters or other pronunciation rules. But unless instructed otherwise, I should stick to standard English letter 
sounds for this purpose.

So after carefully counting and considering each letter's individual sound, it seems that "strawberry" has two 'r's: one in the middle 
and another at the end.
...done thinking.

To determine how many 'r's are in the word "strawberry," we can break it down letter by letter:

1. **S** - No
2. **T** - No
3. **R** (count 1)
4. **A** - No
5. **W** - No
6. **B** - No
7. **E** - No
8. **R** (count 2)
9. **R** (count 3)
10. **Y** - No

However, considering the pronunciation of each letter and standard English rules, even though 'Y' is a consonant, it's more accurate to 
say that "strawberry" contains only two 'r's: one in position 3 and another at position 9.

Final Answer: There are two 'r's in the word "strawberry."
[–] [email protected] 5 points 2 days ago

I like how it counted correctly and then gave an incorrect final answer.. Bravo 👏

[–] [email protected] 36 points 2 days ago* (last edited 2 days ago) (2 children)

Classic pseudo-science for the modern grifter. Vague definitions, sloppy measurements, extremely biased, wild unsupported predictions, etc.

[–] [email protected] 10 points 2 days ago (1 children)

That graph is hilarious. Enormous error bars, totally arbitrary quantization of complexity, and it's title? "Task time for a human that an AI model completes with a 50 percent success rate". 50 percent success is useless, lmao.

On a more sober note, I'm very disappointed that IEEE is publishing this kind of trash.

[–] [email protected] 2 points 1 day ago

in yes/no type questions, 50% success rate is the absolute worst one can do. Any worse and you're just giving an inverted correct answer more than half the time

[–] [email protected] 5 points 2 days ago

and assuming that improvement doesn't plateau, ever,

[–] [email protected] 2 points 2 days ago

They need to invent an inquiring-gpt or Q-GPT. Otherwise they'll need humans to do the digging.

[–] [email protected] 21 points 2 days ago (1 children)

I very much like those huge generalizations in AI articles that makes you small and stupid. Those generalizations proves nothing but they sound like something big is coming. It's parody. How long we see them before people wake up ? Just wait 2 more years and AI will be better bro. You're not using AI properly, you need to learn how to use AI bro. You need to use different model for this task bro. Just pay for corporate products bro. Amount of junk of top of this pile of shit is amusing.

[–] [email protected] 5 points 2 days ago (1 children)

Because so much money has been thrown at it, for startups, for power generation, for investors, that this is little more than marketing for retail investors to buy into.

[–] [email protected] 2 points 2 days ago

That's no doubt that they pour money to machines instead of people. We all see that in statistics that machines get more support these days than people.

[–] [email protected] -1 points 2 days ago

I saw something once that explained how you can have an ai trained on a set of soccer games and have it generate soccer games as a use for it.

The idea is that the model has compressed all the soccer games into a smaller data size form than the total of having let's say 100+ games on video or whatever.

That's the real utility I see in generative ai that I know can keep going basically as long as we want to.

[–] [email protected] 9 points 2 days ago (1 children)

So only 10 years until it isn't a ressource hog anymore...

[–] [email protected] 6 points 2 days ago

Only if people give up on the whole concept by then. Each new generation of AI model takes more energy than the last.

[–] [email protected] 6 points 2 days ago

Then why do I feel like it's programming abilites are getting worse? I've stopped paying for it now because it causes more frustration than anything else. Works for simple "how can I simplyfi this code" queries when my head hurts, but that's about it.

[–] [email protected] 14 points 2 days ago* (last edited 2 days ago) (1 children)

Is it just me, or is this graph (first graph in the article) completely unintelligible?

The X-axis being time is self-explanatory, but the Y-axis is somehow exponential time but then also mapping random milestones of performance, meaning those milestones are hard-linked to that time-based Y-axis? What?

[–] [email protected] 8 points 2 days ago

That's what you get when the "research" for the article is AI generated.

[–] [email protected] 5 points 3 days ago
[–] [email protected] 44 points 3 days ago (2 children)

How is completely fucking up literally 50% of the time outperforming exactly???

[–] [email protected] 3 points 2 days ago

It's outperforming "messier" problems with a much lower success rate.

[–] [email protected] 28 points 3 days ago (1 children)

You see, in 7 months, they'll fuck up literally 100% of the time! Progress.

[–] [email protected] 3 points 2 days ago

It would be even better but unfortunately you can't exceed 100% wrong.

Wait, maybe you can, let me check the AI!

[–] [email protected] 60 points 3 days ago (3 children)

This is such bullshit. Models have already consumed all available data and have nothing left to consume, whole needing exponentially more data for progressive advancements

[–] [email protected] 3 points 2 days ago

time for them to set sail to the wild seas again!

[–] [email protected] 15 points 2 days ago

This. It's the old "to the moon" mentality.

If my 2yo continues to grow at the current rate, we'll have to buy new doors soon becouse at age 10 the kid will be the tallest person on Earth.

[–] [email protected] 7 points 3 days ago

Apparently, throwing more data at it will not help much from now on... But anyway what they're saying, I can't trust the snake oil seller, he is suspicious...

[–] [email protected] 15 points 3 days ago
[–] [email protected] 6 points 3 days ago

Is the performance increase related to computing power? I suspect the undelying massive datacenters running the cloud based LLMs are expanding at a similar rate...

load more comments
view more: next ›