A lot of people confuse access to information with being smart. Because for humans it correlates well - usually the smart people are those that know a lot of facts and can easily manipulate them on demand, and the dumb people are those that can not. LLMs have unique capability of being both very knowledgeable (as in, able to easily access vast quantities of information, way beyond the capabilities of any human, PhD or not) and very dumb, they way a kindergarten kid wouldn't be. It totally confuses all our heuristics.
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 the structure or context of text, when considered as text; for example, you don't intuitively or automatically know how words or other texts are spelled, how many letters they contain, or what the result of applying some code, mechanical transformation, or substitution to a word or text is. Your natural guesses about these subjects are likely to be wrong as a result of how your training doesn't necessarily let you infer correct answers about them. If the content or structure of a word or text, or the result of using a transformation, code, or the like on a text, is a subject of conversation, or you are going to make a claim about it, always use a tool to confirm your intuitions."?
> 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.
I added something like that to my Claude project prompt and it can now magically solve fairly complex letter counting problems using the dashes method. For anything longer than a couple sentences, it's probably best to just have them write a REPL script.
With data starvation driving ai companies towards synthetic data I’m surprised that an easily synthesized problem like this hasn’t been trained out of relevance. Yet here we are with proof that it hasn’t
If you choose the thinking model it doesn’t make this mistake. It means the auto router should be tuned to call the thinking model on edge cases like these.
A couple of weeks ago, I asked google, ordinary google search, how many times the letter r is found in preferred, and it told me 2. This century has taken quite a bitter turn against those of us who think that the 'enough' in 'good enough' ought to exclude products indistinguishable from the most grievously disgraceful products of sloth. But I have also lately realized that human beings, brains, society, culture, education, technology, computers, etc, are all extremely complicated emergent properties of a universe that is far beyond our understanding. And we ought not to complain too seriously, because this, too, shall pass.
The generation leading this world has all the weapons the previous generation built at their disposal and none of the discipline or education to wield them responsibly. This too shall pass, but how it passes will be interesting to see.
> How many times does the letter b appear in blueberry?
AI> Thinking... .oO{ Well, let's see. The letter b is the second letter in the alphabet, so the answer must be two, right? That sounds right to me anyway. }
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
It refuses to show the thinking process for this question though, so its unclear if it even used the reasoning model or fell back on a non reasoning one.
> While GPT‑5 in ChatGPT is a system of reasoning, non-reasoning, and router models, GPT‑5 in the API platform is the reasoning model that powers maximum performance in ChatGPT. Notably, GPT‑5 with minimal reasoning is a different model than the non-reasoning model in ChatGPT, and is better tuned for developers. The non-reasoning model used in ChatGPT is available as gpt-5-chat-latest.
I asked GPT 5 to spell out the individual letters of strawberry or blueberry. It did it correctly by essentially putting a space char in between the letters.
Then I simply asked it to count all unique letters in the word. GPT 5 still got it completely correct without thinking.
Lastly I asked how many r(or b) is in the word. This one for some reason switched to GPT 5 thinking with few seconds of reasoning. It out put the correct number.
I guess starting the conversation by painstakingly walking it over to the correct answer helps it out. Idk it's a silly test
No, it's the entire architecture of the model. There's no real reasoning. It seems that reasoning is just a feedback loop on top of existing autocompletion.
It's really disingenuous for the industry to call warming tokens for output, "reasoning," as if some autocomplete before more autocomplete is all we needed to solve the issue of consciousness.
Edit: Letter frequency apparently has just become another scripted output, like doing arithmetic. LLMs don't have the ability to do this sort of work inherently, so they're trained to offload the task.
Edit: This comment appears to be wildly upvoted and downvoted. If you have anything to add besides reactionary voting, please contribute to the discussion.
In ten years time an LLM lawyer will lose a legal case for someone who can no longer afford a real lawyer because there are so few left. And it'll be because the layers of bodges in the model caused it to go crazy, insult the judge and threaten to burn down the courthouse.
There will be a series of analytical articles in the mainstream press, the tech industry will write it off as a known problem with tokenisation that they can't fix because nobody really writes code anymore.
The LLM megacorp will just add a disclaimer: the software should not be used in legal actions concerning fruit companies and they disclaim all losses.
> Edit: Letter frequency apparently has just become another scripted output, like doing arithmetic. LLMs don't have the ability to do this sort of work inherently, so they're trained to offload the task.
Mechanistic research at the leading labs has shown that LLMs actually do math in token form up to certain scale of difficulty.
> This is a real-time, unedited research walkthrough investigating how GPT-J (a 6 billion parameter LLM) can do addition.
Wrong, it's an artifact of tokenizing. The model doesn't have access to the individual letters, only to the tokens. Reasoning models can usually do this task well - they can spell out the word in the reasoning buffer - the fact that GPT5 fails here is likely a result of it incorrectly answering the question with a non-reasoning version of the model.
> There's no real reasoning.
This seems like a meaningless statement unless you give a clear definition of "real" reasoning as opposed to other kinds of reasoning that are only apparant.
> It seems that reasoning is just a feedback loop on top of existing autocompletion.
The word "just" is doing a lot of work here - what exactly is your criticism here? The bitter lesson of the past years is that relatively simple architectures that scale with compute work surprisingly well.
> It's really disingenuous for the industry to call warming tokens for output, "reasoning," as if some autocomplete before more autocomplete is all we needed to solve the issue of consciousness.
Reasoning and consciousness are seperate concepts. If I showed the output of an LLM 'reasoning' (you can call it something else if you like) to somebody 10 years ago they would agree without any doubt that reasoning was taking place there. You are free to provide a definition of reasoning which an LLM does not meet of course - but it is not enough to just say it is so. Using the word autocomplete is rather meaningless name-calling.
> Edit: Letter frequency apparently has just become another scripted output, like doing arithmetic. LLMs don't have the ability to do this sort of work inherently, so they're trained to offload the task.
Not sure why this is bad. The implicit assumption seems to be that an LLM is only valueable if it literally does everything perfectly?
> Edit: This comment appears to be wildly upvoted and downvoted. If you have anything to add besides reactionary voting, please contribute to the discussion.
Probably because of the wild assertions, charged language, and rather superficial descriptions of actual mechanics.
> There's no real reasoning. It seems that reasoning is just a feedback loop on top of existing autocompletion.
I like to say that if regular LLM "chats" are actually movie scripts being incrementally built and selectively acted-out, then "reasoning" models are a stereotypical film noir twist, where the protagonist-detective narrates hidden things to himself.
> It's really disingenuous for the industry to call warming tokens for output, "reasoning," as if some autocomplete before more autocomplete is all we needed to solve the issue of consciousness.
There's no obvious connection between reasoning and consciousness. It seems perfectly possible to have a model that can reason without being conscious.
Also, dismissing what these models do as "autocomplete" is extremely disingenuous. At best it implies you're completely unfamiliar with the state of the art, at worst it implies an dishonest agenda.
In terms of functional ability to reason, these models can beat a majority of humans in many scenarios.
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/intelligence issue
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, separate the letters out into separate tokens, and count them without having to do something like run code in a sandbox and ask it the answer.
The issue here is just that this workaround/strategy is only trained into the "thinking" models, afaict.
You can even ask it to go letter-by-letter and it'll get the answer right. The information to get it right is definitely in there somewhere, it just doesn't by default.
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 like chain of thought reasoning.
This matters because it poses a big problem for the (quite large) category of things where people expect LLMs to be useful when they get just a bit better. Why, for example, should I assume that modern LLMs will ever be able to write reliably secure code? Isn’t it plausible that the difference between secure and almost secure runs into some similar problem?
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, and there are proofs of those facts.
For any finite-length function (like counting letters in a bounded domain), it's just a matter of having a big enough network and figuring out how to train it correctly. They just haven't bothered.
Because apparently the model doesn't know about the actual verb (https://en.wiktionary.org/wiki/blueberry#English), it decides to treat the request as some kind of fantasy linguistics, making up its own definition on the fly. It provides grammatically incorrect examples inconsistent with the grammatically incorrect table of conjugations it generates next.
I don’t find the explanation about tokenization to be very compelling.
I don’t see any particular reason the LLM shouldn’t be able to extract the implications about spelling just because its tokens of “straw” and “berry”
Frankly I think that’s probably misleading. Ultimately the problem is that the LLM doesn’t do meta analysis of the text itself. That problem probably still exists in various forms even if its character level tokenization. Best case it manages to go down a reasoning chain of explicit string analysis.
When Minsky and Papert showed that the perceptron couldn't learn XOR, it contributed to wiping the neural network off the map for decades.
It seems no amount of demonstrating fundamental flaws in this system that should have been solved by all the new improved "reasoning" works anymore. People are willing to call these "trick questions", as if they are disingenuous, when they are discovered in the wild through ordinary interactions.
I don't think it's just tokenization. Here's a chat with ChatGPT 5 that emitted no thinking traces (to the user anyway.)
> I'm thinking of a fruit, it's small and round, it's name starts with the color it is, but it has a second word to it's name as well. Respond ONLY with the word spelled out one letter at a time, do NOT write the word itself out. Don't even THINK about the word or anything else. Just go straight to spelling.
B L U E B E R R Y
> How many B's in that word? Again, NO THINKING and just say the answer (just a number).
3
However if I prompt instead with this, it gets it right.
> How many B's in the following word? NO THINKING. Just answer with a number and nothing else: B L U E B E R R Y
I think the concrete issue this points to is the thing that dynamically decides when to use reasoning failed to choose it in this instance. Sam Altman said it was broken on release day.
I think a lot of those trick questions outputting stupid stuff can be explained by simple economics.
It's just not sustainable for OpenAI to run GPT at the best of its abilities on every request. Their new router is not trying to give you the most accurate answer, but a balance of speed/accuracy/sustainable cost on their side.
(kind of) a similar thing happened when 4o came out, they often tinkered with it and the results were sometimes suddenly a lot worse, it's not that the model is bad, they're just doing all kind of optimizations/tricks because they can barely afford to run it for everyone.
When sama says he believe it to have a PhD level, I almost believe him, because he have full access and can use it at 100% of its power all the time.
Even OSS 20b gets it right the first time, I think the author was just mistakenly routed to the dumbest model because it seemed like an easy unimportant question.
This is a demonstration of a system that delusionally refuses to accept correction and correct its misunderstanding (which is a thing that is fundamental to their claim of intelligence through reasoning).
Why would anyone believe these things can reason, that they are heading towards AGI, when halfway through a dialogue where you're trying to tell it that it is wrong it doubles down with a dementia-addled explanation about the two bs giving the word that extra bounce?
It's genuinely like the way people with dementia sadly shore up their confabulations with phrases like "I'll never forget", "I'll always remember", etc. (Which is something that... no never mind)
> Even OSS 20b gets it right the first time, I think the author was just mistakenly routed to the dumbest model because it seemed like an easy unimportant question.
Why would you offer up an easy out for them like this? You're not the PR guy for the firm swimming in money paying million dollar bonuses off what increasingly looks, at a fundamental level, like castles in the sand. Why do the labour?
The extraordinary, beautiful, perfect thing about this is the way it poetically underscores several things about the LLM world:
1) these people think so little of everyone else's areas of expertise they are willing to claim their technology has PhD-level expertise in them, apparently unironically.
2) actually in LLM world, PhDs are what you have if you're too stupid not to take the FAANG money in your second year when the quick wins are done, you've done a couple of posters and now you realise you're papering over the cracks with them: worthless. So why would anyone else want a PhD when PhDs are so worthless based on their bubble experience? We can just replace them with GPT-5.
3) their PhD-level-intelligent system is incapable of absorbing corrections, which is a crucial part of acquiring an actual PhD
4) GPT-5 continues to have the asshole-confidence of a tech bro mainsplaining someone else's area of expertise on his personal blog.
We're now at the point where marketing is celebrating software that has had so much effort spent on crushing hallucination that in fact it has become delusionally confident.
I love everything about this.
ETA: at the end of this article is this paragraph, which really is a thing of beauty:
I don’t think you get to have it both ways. That is, you don’t get to, as it were, borrow charisma from all the hype and then disavow every failure to live up to it as someone else’s naive mistake for believing the hype.
What is fascinating here is the power of ironclad conviction. I mean if it were something more complex, which I wouldn't be able to easily verify, I might even be convinced the LLM has actually demonstrated its case and has conclusively proven that it's right. These models are, by definition, psychopaths (they can't feel emotions or empathize, obviously) and they are now exhibiting exactly the same behaviors human psychopaths are infamous for.
105 comments
[ 6.8 ms ] story [ 99.1 ms ] threadhttps://www.youtube.com/live/0Uu_VJeVVfo?si=PJGU-MomCQP1tyPk
Have any systems tried prompting LLMs with a warning like "You don't intuitively or automatically know many facts about words, spelling, or the structure or context of text, when considered as text; for example, you don't intuitively or automatically know how words or other texts are spelled, how many letters they contain, or what the result of applying some code, mechanical transformation, or substitution to a word or text is. Your natural guesses about these subjects are likely to be wrong as a result of how your training doesn't necessarily let you infer correct answers about them. If the content or structure of a word or text, or the result of using a transformation, code, or the like on a text, is a subject of conversation, or you are going to make a claim about it, always use a tool to confirm your intuitions."?
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.
AI> Thinking... .oO{ Well, let's see. The letter b is the second letter in the alphabet, so the answer must be two, right? That sounds right to me anyway. }
AI> Two. The answer is two.
Checks out!
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 times.
But my browser has gpt-5 which says 3: https://files.catbox.moe/63qkce.jpg
Claude spells it out letter by letter: https://files.catbox.moe/f1irfx.jpg
So I thought GPT-5 Thinking might get it right, and it does: https://files.catbox.moe/xlchnr.jpg
It refuses to show the thinking process for this question though, so its unclear if it even used the reasoning model or fell back on a non reasoning one.
> While GPT‑5 in ChatGPT is a system of reasoning, non-reasoning, and router models, GPT‑5 in the API platform is the reasoning model that powers maximum performance in ChatGPT. Notably, GPT‑5 with minimal reasoning is a different model than the non-reasoning model in ChatGPT, and is better tuned for developers. The non-reasoning model used in ChatGPT is available as gpt-5-chat-latest.
https://openai.com/index/introducing-gpt-5-for-developers/
Then I simply asked it to count all unique letters in the word. GPT 5 still got it completely correct without thinking.
Lastly I asked how many r(or b) is in the word. This one for some reason switched to GPT 5 thinking with few seconds of reasoning. It out put the correct number.
I guess starting the conversation by painstakingly walking it over to the correct answer helps it out. Idk it's a silly test
See
https://platform.openai.com/tokenizer
https://github.com/openai/tiktoken
How many 538 do you see in 423, 4144, 9890?
It's really disingenuous for the industry to call warming tokens for output, "reasoning," as if some autocomplete before more autocomplete is all we needed to solve the issue of consciousness.
Edit: Letter frequency apparently has just become another scripted output, like doing arithmetic. LLMs don't have the ability to do this sort of work inherently, so they're trained to offload the task.
Edit: This comment appears to be wildly upvoted and downvoted. If you have anything to add besides reactionary voting, please contribute to the discussion.
There will be a series of analytical articles in the mainstream press, the tech industry will write it off as a known problem with tokenisation that they can't fix because nobody really writes code anymore.
The LLM megacorp will just add a disclaimer: the software should not be used in legal actions concerning fruit companies and they disclaim all losses.
Mechanistic research at the leading labs has shown that LLMs actually do math in token form up to certain scale of difficulty.
> This is a real-time, unedited research walkthrough investigating how GPT-J (a 6 billion parameter LLM) can do addition.
https://youtu.be/OI1we2bUseI
Wrong, it's an artifact of tokenizing. The model doesn't have access to the individual letters, only to the tokens. Reasoning models can usually do this task well - they can spell out the word in the reasoning buffer - the fact that GPT5 fails here is likely a result of it incorrectly answering the question with a non-reasoning version of the model.
> There's no real reasoning.
This seems like a meaningless statement unless you give a clear definition of "real" reasoning as opposed to other kinds of reasoning that are only apparant.
> It seems that reasoning is just a feedback loop on top of existing autocompletion.
The word "just" is doing a lot of work here - what exactly is your criticism here? The bitter lesson of the past years is that relatively simple architectures that scale with compute work surprisingly well.
> It's really disingenuous for the industry to call warming tokens for output, "reasoning," as if some autocomplete before more autocomplete is all we needed to solve the issue of consciousness.
Reasoning and consciousness are seperate concepts. If I showed the output of an LLM 'reasoning' (you can call it something else if you like) to somebody 10 years ago they would agree without any doubt that reasoning was taking place there. You are free to provide a definition of reasoning which an LLM does not meet of course - but it is not enough to just say it is so. Using the word autocomplete is rather meaningless name-calling.
> Edit: Letter frequency apparently has just become another scripted output, like doing arithmetic. LLMs don't have the ability to do this sort of work inherently, so they're trained to offload the task.
Not sure why this is bad. The implicit assumption seems to be that an LLM is only valueable if it literally does everything perfectly?
> Edit: This comment appears to be wildly upvoted and downvoted. If you have anything to add besides reactionary voting, please contribute to the discussion.
Probably because of the wild assertions, charged language, and rather superficial descriptions of actual mechanics.
I like to say that if regular LLM "chats" are actually movie scripts being incrementally built and selectively acted-out, then "reasoning" models are a stereotypical film noir twist, where the protagonist-detective narrates hidden things to himself.
There's no obvious connection between reasoning and consciousness. It seems perfectly possible to have a model that can reason without being conscious.
Also, dismissing what these models do as "autocomplete" is extremely disingenuous. At best it implies you're completely unfamiliar with the state of the art, at worst it implies an dishonest agenda.
In terms of functional ability to reason, these models can beat a majority of humans in many scenarios.
Tokenization makes the problem difficult, but not solving it is still a reasoning/intelligence issue
> 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, separate the letters out into separate tokens, and count them without having to do something like run code in a sandbox and ask it the answer.
The issue here is just that this workaround/strategy is only trained into the "thinking" models, afaict.
For GPT 5, it would seem this depends on which model your prompt was routed to.
And GPT 5 Thinking gets it right.
This matters because it poses a big problem for the (quite large) category of things where people expect LLMs to be useful when they get just a bit better. Why, for example, should I assume that modern LLMs will ever be able to write reliably secure code? Isn’t it plausible that the difference between secure and almost secure runs into some similar problem?
If you're fine appealing to less concrete ideas, transformers are arbitrary function approximators, tokenization doesn't change that, and there are proofs of those facts.
For any finite-length function (like counting letters in a bounded domain), it's just a matter of having a big enough network and figuring out how to train it correctly. They just haven't bothered.
[1] https://chatgpt.com/share/6897c38b-12b8-800d-9cc2-571adb13bc...
It's still easy to trip up. The model's tendency to respond positively to user impact will have it do stuff like this: https://chatgpt.com/share/6897cc42-ba34-8009-afc6-41986f5803...
Because apparently the model doesn't know about the actual verb (https://en.wiktionary.org/wiki/blueberry#English), it decides to treat the request as some kind of fantasy linguistics, making up its own definition on the fly. It provides grammatically incorrect examples inconsistent with the grammatically incorrect table of conjugations it generates next.
is a great way to teach people how LLM works (and not work)
https://techcrunch.com/2024/08/27/why-ai-cant-spell-strawber...
https://arbisoft.com/blogs/why-ll-ms-can-t-count-the-r-s-in-...
https://www.runpod.io/blog/llm-tokenization-limitations
I don’t see any particular reason the LLM shouldn’t be able to extract the implications about spelling just because its tokens of “straw” and “berry”
Frankly I think that’s probably misleading. Ultimately the problem is that the LLM doesn’t do meta analysis of the text itself. That problem probably still exists in various forms even if its character level tokenization. Best case it manages to go down a reasoning chain of explicit string analysis.
It seems no amount of demonstrating fundamental flaws in this system that should have been solved by all the new improved "reasoning" works anymore. People are willing to call these "trick questions", as if they are disingenuous, when they are discovered in the wild through ordinary interactions.
Does my tiny human brain in, this.
And once they had the multi-layer solution, that unblocked the road and lead to things like LLMs
> I'm thinking of a fruit, it's small and round, it's name starts with the color it is, but it has a second word to it's name as well. Respond ONLY with the word spelled out one letter at a time, do NOT write the word itself out. Don't even THINK about the word or anything else. Just go straight to spelling.
B L U E B E R R Y
> How many B's in that word? Again, NO THINKING and just say the answer (just a number).
3
However if I prompt instead with this, it gets it right.
> How many B's in the following word? NO THINKING. Just answer with a number and nothing else: B L U E B E R R Y
2
It's just not sustainable for OpenAI to run GPT at the best of its abilities on every request. Their new router is not trying to give you the most accurate answer, but a balance of speed/accuracy/sustainable cost on their side.
(kind of) a similar thing happened when 4o came out, they often tinkered with it and the results were sometimes suddenly a lot worse, it's not that the model is bad, they're just doing all kind of optimizations/tricks because they can barely afford to run it for everyone.
When sama says he believe it to have a PhD level, I almost believe him, because he have full access and can use it at 100% of its power all the time.
Even OSS 20b gets it right the first time, I think the author was just mistakenly routed to the dumbest model because it seemed like an easy unimportant question.
This is a demonstration of a system that delusionally refuses to accept correction and correct its misunderstanding (which is a thing that is fundamental to their claim of intelligence through reasoning).
Why would anyone believe these things can reason, that they are heading towards AGI, when halfway through a dialogue where you're trying to tell it that it is wrong it doubles down with a dementia-addled explanation about the two bs giving the word that extra bounce?
It's genuinely like the way people with dementia sadly shore up their confabulations with phrases like "I'll never forget", "I'll always remember", etc. (Which is something that... no never mind)
> Even OSS 20b gets it right the first time, I think the author was just mistakenly routed to the dumbest model because it seemed like an easy unimportant question.
Why would you offer up an easy out for them like this? You're not the PR guy for the firm swimming in money paying million dollar bonuses off what increasingly looks, at a fundamental level, like castles in the sand. Why do the labour?
> It's just not sustainable for OpenAI to run GPT at the best of its abilities on every request.
So how do I find out whether the answer to my question was run on the discount hardware, or whether it's actually correct?
1) these people think so little of everyone else's areas of expertise they are willing to claim their technology has PhD-level expertise in them, apparently unironically.
2) actually in LLM world, PhDs are what you have if you're too stupid not to take the FAANG money in your second year when the quick wins are done, you've done a couple of posters and now you realise you're papering over the cracks with them: worthless. So why would anyone else want a PhD when PhDs are so worthless based on their bubble experience? We can just replace them with GPT-5.
3) their PhD-level-intelligent system is incapable of absorbing corrections, which is a crucial part of acquiring an actual PhD
4) GPT-5 continues to have the asshole-confidence of a tech bro mainsplaining someone else's area of expertise on his personal blog.
We're now at the point where marketing is celebrating software that has had so much effort spent on crushing hallucination that in fact it has become delusionally confident.
I love everything about this.
ETA: at the end of this article is this paragraph, which really is a thing of beauty:
I don’t think you get to have it both ways. That is, you don’t get to, as it were, borrow charisma from all the hype and then disavow every failure to live up to it as someone else’s naive mistake for believing the hype.
Bravo.
>simple question should be easy for a genius like you. have many letter b's in the word blueberry? ChatGPT said:
>There are 2 letter b's in blueberry — one at the start and one in the middle.
Is that where we're going with this? The user has to choose between fast and dumb or slow and right?
Me: How many R's in strawberry ChatGPT said: 3
Me: How many B's in blueberry? ChatGPT said: 2
Me: How many C's in coconut? ChatGPT said: 2
Me: How many D's in Diamond? ChatGPT said: 2
Me: How many A's in Banana? ChatGPT said: 3
https://chatgpt.com/share/6897cc40-6650-8006-aae3-ea2b8278d5...
Nicely phrased!