Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-5: "How many times does the letter b appear in blueberry?"

bsky.app

Post reply on HN
Print view View original

161–170 of 339 posts

Re: GPT-5: "How many times does the letter b appear in blueberry?"

#161

Post by tibbar »

windowshopping wrote: post #144
mikehearn wrote: post #132

This is a well known blindspot for LLMs. It's the machine version of showing a human an optical illusion and then judging their intelligence when they fail to perceive the reality of the image (the gray box example at the top of https://en.wikipedia.org/wiki/Optical_illusion is a good example). The failure is a result of their/our fundamental architecture.

What a terrible analogy. Illusions don't fool our intelligence, they fool our senses, and we use our intelligence to override our senses and see it for what it for it actually is - which is exactly why we find them interesting and have a word for them. Because they create a conflict between our intelligence and our senses. The machine's senses aren't being fooled. The machine doesn't have senses. Nor does it have int…

Really? I thought the analogy was pretty good. Here senses refer to how the machines perceive text, IE as tokens that don't correspond 1:1 to letters. If you prefer a tighter comparison, suppose you ask an English speaker how many vowels are in the English transliteration of a passage of Chinese characters. You could probably figure it out, but it's not obvious, and not easy to do correctly without a few rounds of calculations.

The point being, the whole point of this question is to ask the machine something that's intrinsically difficult for it due to its encoding scheme for text. There are many questions of roughly equivalent complexity that LLMs will do fine at because they don't poke at this issue. For example:

``` how many of these numbers are even?

12 2 1 3 5 8

```

Re: GPT-5: "How many times does the letter b appear in blueberry?"

#162

Post by zahlman »

xenotux wrote: post #155
mikehearn wrote: post #132

This is a well known blindspot for LLMs. It's the machine version of showing a human an optical illusion and then judging their intelligence when they fail to perceive the reality of the image (the gray box example at the top of https://en.wikipedia.org/wiki/Optical_illusion is a good example). The failure is a result of their/our fundamental architecture.

OpenAI codenamed one of their models "Project Strawberry" and IIRC, Sam Altman himself was taking a victory lap that it can count the number of "r"s in "strawberry". Which I think goes to show that it's hard to distinguish between LLMs getting genuinely better at a class of problems versus just being fine-tuned for a particular benchmark that's making rounds.

See also the various wolf/goat/cabbage benchmarks, or the crossing a bridge at various speeds with limited light sources benchmarks.

Re: GPT-5: "How many times does the letter b appear in blueberry?"

#163

Post by russellbeattie »

Just tried it a few times on Gemini 2.5 Flash, as well as the letter r in strawberry, e in housekeeper, h in hitchhiker, and i in supercalifragilisticexpialidocious.

They were all correct.

Not sure what exactly this proves or doesn't prove, but I figured I'd add it for posterity.

Re: GPT-5: "How many times does the letter b appear in blueberry?"

#165

Post by zahlman »

asadotzler wrote: post #128
mikewarot wrote: post #114

Why don't people here on HN understand that LLMs never see ASCII or other raw characters as input? Expecting spelling, rhyming, arithmetic or other character oriented responses will always yield disappointing results.

We do understand. We don't think that's okay. If a model cannot manage character level consideration, that's a serious flaw that's got potential to lead to an immeasurable number of failure states. "Duh, of course it can't count" is not the best look for a bot whose author tells us it's got PhD-level skill.

I do think it's "okay". After all, it's clear that fixing it would require a fundamentally different approach.

I just also think it's a reason to mock people who don't try to understand those limitations and get way ahead of themselves hyping up the technology.

The entire point of this exercise is to refute the claim that LLMs are a step towards AGI, even given "agency". And we should be happy that they aren't — because supposing that AGI is possible, the way that we currently treat LLMs shows that we as a species are nowhere near ready for the consequences of creating it.

Re: GPT-5: "How many times does the letter b appear in blueberry?"

#166

Post by zeroonetwothree »

sdenton4 wrote: post #134
arduanika wrote: post #121

Earlier quoted context omitted.

Because the damn things are marketed under the word "intelligence". That word used to mean something.

It's an umwelt problem. Bats think we're idiots because we don't hear ultrasonic sound, and thus can't echolocate. And we call the LLMs idiots because they consume tokenized inputs, and don't have access to the raw character stream.

Pretty sure bats don’t think about human intelligence at all.

Re: GPT-5: "How many times does the letter b appear in blueberry?"

#168

Post by pxc »

johnecheck wrote: post #151
pxc wrote: post #127

Earlier quoted context omitted.

Here's an example of what gpt-oss-20b (at the default mxfp4 precision) does with this question: > How many "s"es are in the word "Mississippi"? The "thinking portion" is: > Count letters: M i s s i s s i p p i -> s appears 4 times? Actually Mississippi has s's: positions 3,4,6,7 = 4. The answer is: > The word “Mississippi” contains four letter “s” s. They can indeed do some simple pattern matching on the query, separ…

That proves nothing. The fact that Mississippi has 4 "s" is far more likely to be in the training data than the fact that blueberry has 2 "b"s. And now that fact is going to be in the data for the next round of training. We'll need to need to try some other words on the next model.

It does the same thing with a bunch of different words like "committee", "disestablishmentarianism", "dog", "Anaxagoras", and a string I typed by mashing the keyboard, "jwfekduadasjeudapu". It seems fairly general and to perform pretty reliably.

(Sometimes the trace is noisier, especially in quants other than the original.)

This task is pretty simple and I think can be solved easily with the same kind of statistical pattern matching these models use to write other text.

Re: GPT-5: "How many times does the letter b appear in blueberry?"

#169

Post by mdp2021 »

kgeist wrote: post #158
mdp2021 wrote: post #122

I have done this test extensively days ago, on a dozen models: no one could count - all of them got results wrong, all of them suggested they can't check and will just guess. Until they will be able of procedural thinking they will be radically, structurally unreliable. Structurally delirious. And it is also a good thing that we can check in this easy way - if the producers patched the local fault only, then the abse…

Did you enable reasoning? Qwen3 32b with reasoning enabled gave me the correct answer on the first attempt.

> Did you enable reasoning

Yep.

> gave me the correct answer

Try real-world tests that cannot be covered by training data or chancey guesses.

Re: GPT-5: "How many times does the letter b appear in blueberry?"

#170

Post by rambambram »

skybrian wrote: post #71
coldtea wrote: post #16

Q: How many times does the letter b appear in blueberry? The letter “b” appears 3 times in the word blueberry: • 1st b – at the beginning: Blueberry • 2nd b – in the middle: blueberry • 3rd b – again in the middle: blueberry (wait… no — actually…) Let’s break it down carefully: blueberry → b, l, u, e, b, e, r, r, y Letters: 1. b 2. l 3. u 4. e 5. b 6. e 7. r 8. r 9. y So the letter b appears twice. Final answer: 2 ti…

How did you generate this?

Notepad and a keyboard
Post reply on HN