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

151–160 of 339 posts

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

#151

Post by johnecheck »

pxc wrote: post #127
wongarsu wrote: post #36

Earlier quoted context omitted.

It can spell the word (writing each letter in uppercase followed by a whitespace, which should turn each letter with its whitespace into a separate token). It also has reasoning tokens to use as scratch space, and previous models have demonstrated knowledge of the fact that spelling words is a useful step to counting letters. Tokenization makes the problem difficult, but not solving it is still a reasoning/intelligen…

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.

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

#152

Post by kgeist »

Qwen3 32b with reasoning (which I run locally) gives the correct answer. A pretty good model for its size.

Pretty sure GPT5 with reasoning should be able to solve it, too. I guess the real problem here is that GPT5's router doesn't understand that it's a problem which requires reasoning.

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

#153

Post by mdp2021 »

schoen wrote: post #4

These are always amazing when juxtaposed with apparently impressive LLM reasoning, knowledge, and creativity. You can trivially get them to make the most basic mistakes about words and numbers, and double down on those mistakes, repeatedly explaining that they're totally correct. Have any systems tried prompting LLMs with a warning like "You don't intuitively or automatically know many facts about words, spelling, or…

> prompting LLMs with a warning like "You don't intuitively or automatically know many facts about...

We are not interested specifically in the inability to «know» about text: we are strongly interested in general in the ability to process ideas consciously, procedurally - and the inability to count suggests the general critical fault.

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

#154

Post by cute_boi »

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.

The only issue is they shouldn't call it PHD level intelligence when they can't do simple task like this.

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

#155

Post by xenotux »

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.

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

#156

Post by patrickhogan1 »

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.

Except the reasoning model o3 and GPT5 thinking can get the right answer. Humans use reasoning.

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

#157

Post by viraptor »

hansvm wrote: post #103
amai wrote: post #22

Isn't that just an artifact caused by the tokenization of the training and input data? See https://platform.openai.com/tokenizer https://github.com/openai/tiktoken

Common misconception. That just means the algorithm for counting letters can't be as simple as adding 1 for every token. The number of distinct tokens is tiny compared to the parameter space, and it's not infeasible to store a mapping from token type to character count in those weights. If you're fine appealing to less concrete ideas, transformers are arbitrary function approximators, tokenization doesn't change that…

> They just haven't bothered.

Or they don't see the benefit. I'm sure they could train the representation of every token and make spelling perfect. But if you have real users spending money on useful tasks already - how much money would you spend on training answers to meme questions that nobody will pay for. They did it once for the fun headline already and apparently it's not worth repeating.

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

#158

Post by kgeist »

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.

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

#159

Post by zahlman »

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.

In an optical illusion, we perceive something that isn't there due to exploiting a correction mechanism that's meant to allow us to make better practical sense of visual information in the average case.

Asking LLMs to count letters in a word fails because the needed information isn't part of their sensory data in the first place (to the extent that a program's I/O can be described as "sense"). They reason about text in atomic word-like tokens, without perceiving individual letters. No matter how many times they're fed training data saying things like "there are two b's in blueberry", this doesn't register as a fact about the word "blueberry" in itself, but as a fact about how the word grammatically functions, or about how blueberries tend to be discussed. They don't model the concept of addition, or counting; they only model the concept of explaining those concepts.

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

#160

Post by viraptor »

SpicyLemonZest wrote: post #60
amai wrote: post #22

Isn't that just an artifact caused by the tokenization of the training and input data? See https://platform.openai.com/tokenizer https://github.com/openai/tiktoken

It clearly is an artifact of tokenization, but I don’t think it’s a “just”. The point is precisely that the GPT system architecture cannot reliably close the gap here; it’s almost able to count the number of Bs in a string, there’s no fundamental reason you could not build a correct number-of-Bs mapping for tokens, and indeed it often gets the right answer. But when it doesn’t you can’t always correct it with things…

> cannot reliably close the gap here

Have you got any proof they're even trying? It's unlikely that's something their real customers are paying for.

Post reply on HN