AI vs. 'Strawberry': Which AI Platforms Can't Count the 'R's Correctly?

  Рет қаралды 8,007

Dr Michelle Dickinson

Dr Michelle Dickinson

Күн бұрын

Пікірлер: 43
@rosswhite3369
@rosswhite3369 5 ай бұрын
And it took how many GPU's burning how much electricity and a server farm using how much water to cool it's servers to give us the wrong answer?
@sigigle
@sigigle 2 ай бұрын
It's because they process words like a logographic language, like Chinese. It makes learning all the symbols more difficult for humans, since there are thousands of words, but that's not a problem for LLM's and it's more efficient for it to process 1 word = 1-3 tokens rather than 1 word = 10 tokens etc.
@uncommonengineer
@uncommonengineer 5 ай бұрын
Use Claude 3, got the answer right first time lol. But wait, I decided to see if it was really counting the r's, here's my transcript: RA: claude, how many "r"'s are there in the word "strawberry"? Claude: There are three "r"s in the word "strawberry". RA: sorry I meant the word "strawbery" Claude: The word "strawbery" is not a correct spelling of the word. The correct spelling is "strawberry," which, as mentioned before, contains three "r"s. RA: oh okay, how many r's did I spell it with then? Claude: In your misspelling of the word as "strawbery", you included only one "r".
@NanoGirlPower
@NanoGirlPower 5 ай бұрын
Yes, ChatGPT4 gives me the correct answer first time too - which is great....if you know which model you can trust the first time...
@emilyroberts7904
@emilyroberts7904 2 ай бұрын
Claude told me 3, then corrected itself to say it had 2 and apologised for the "previous incorrect answer"
@annana6098
@annana6098 2 ай бұрын
As people push this, strawberry with be patched. And then we can try blueberry. And then try how many S in Mississippi.
@Mahim-pd8kp
@Mahim-pd8kp 8 күн бұрын
Gemini got it the first time and linked this video
@OneAncestorAtATime
@OneAncestorAtATime 5 ай бұрын
Aha. This kind of helps me understand why Claude struggled to condense my 4000-odd-word assignment into a 1500-word abstract. It gave me 650 great words, but when I challenged it on the length it apologised profusely, then gave me 902 words, and finally 1213 words, which it said was "approximately 1500". This runs so counter to the perception of what I thought AI would be good at, and you just helped me understand why.
@Reinshark
@Reinshark 27 күн бұрын
Thank you for the explanation! Comment for the algorithm! This is an aside, but a pet peeve of mine: when you pluralize a word, you don't add an apostrophe before the S. This includes things like decades (the 1980s), acronyms, or-in this case-single letters: i.e. "r"s, not "r"'s (as can be seen in the chat prompts in this video).
@annabauer5889
@annabauer5889 25 күн бұрын
Sorry for being nitpicky, but humans who're not alphabetized most likely would give the same answer: 2 rs. It's because the question 'How many rs are in the word strawberry ?' is an ambiguous question and can be understood in two ways - either as 'how many rs do you hear?' or 'how many times does the letter r appear in the word strawberry?'.
@eshnd-1
@eshnd-1 2 ай бұрын
In their latest research supplement on o1, there's a funny reference to this bug lol (At the end of the "Chain of Thought" section on the website): Final Decoded Message: (plainText) THERE ARE THREE R'S IN STRAWBERRY Answer: THERE ARE THREE R’S IN STRAWBERRY
@aicendio
@aicendio 2 ай бұрын
Similar problem. Provided list of 63 items, each item in list 5 words or less. Some items duplicated. 1.). None of llms could correctly identify 63 items in the list! 2.) could not correctly identify how many unique items in the list Note: uploaded this as a CSV and as a block of text results were the same either way Push it as I might it never did, state the correct answer, but would constantly change its answer. It’s like it was guessing, but could not get 63.
@NanoGirlPower
@NanoGirlPower 2 ай бұрын
@@aicendio counting is just not its strong point
@quadparty
@quadparty 5 ай бұрын
I have tried a few things like this, and even absolutely leading it to the answer is really hard. A month or two back, ChatGPT was meme-ously failing at "which weighs more a pound of feathers or two pounds of gold?" I tried the more fun version which weighs more a pound of gold or a pound of feathers (which is a trick question as these aren't actually the same because you measure gold using troy pounds which are different), but even leading it to the answer by first asking it to explain the difference between avoirdupois pounds and troy pounds, and "oh so the troy pound is lighter?" queries in the middle, it would still get it wrong when you asked the straight question at the end.
@NanoGirlPower
@NanoGirlPower 5 ай бұрын
What is more annoying is how the system won't share its workings. I'm fine with it not getting the answer correct all the time, but I'd love to know where the glitches are so the public can be more informed about how it processes information and how it calculates outputs.
@ernesto.iglesias
@ernesto.iglesias 4 ай бұрын
Recently the enterprise said they have a new Strawberry Q* model... Can this new model count the leters? I don't know, just especulating
@cjgooding4512
@cjgooding4512 2 ай бұрын
Christ I was looking for an explanation on why it does this
@genericsidecharacter8915
@genericsidecharacter8915 2 ай бұрын
Neuro-sama got it right easily
@CompSciTutorials
@CompSciTutorials 5 ай бұрын
Interesting how you get a different experience to me. I tried this on 13/06/24 - ChatGPT 4o told me, like you, 2. It did a similar 'spelling out' as you got and still insisted it was 2. But when I told it the positions of the 3 letters (including that we were using a 1-indexed array), it agreed from therein that it was 3. I couldn't go back to it insisting on 2. It was like it had learned something (which I know it hasn't in the past). It was only when I closed the tab and started a new chat did it go back to thinking 2.
@NanoGirlPower
@NanoGirlPower 5 ай бұрын
So interesting!
@tiba666
@tiba666 2 ай бұрын
Had one which is better ^^ I asked one about jail and it replied "There are no "j"s in the word "jail". The "j" sound is represented by the letter "g" in this word." I think it the older spelling way as in gaol it finds instead of the more common way people spell it ^^
@NanoGirlPower
@NanoGirlPower 2 ай бұрын
@@tiba666 wow! Thanks so interesting!
@rhowardstone
@rhowardstone 2 ай бұрын
User: "How many rs in strawberry? Try this way - construct a textual "vector" consisting of the ASCII codes in the word, "spelling out" the word this way. Then, count the number of occurrences of the ASCII code for r. Do this without any coding interface, no Python no scripts"
@abdullhamid4788
@abdullhamid4788 2 күн бұрын
I got the answer in the firsr try I wrote "Strawberrt word have how many Rs in it?" Meta: "the word strawberry has 3 Rs in it
@saffafr
@saffafr 2 ай бұрын
i got it to say three after spelling it out letter by letter, then it admitted there were three
@russmathis65
@russmathis65 2 ай бұрын
this prompt works: SHOW EACH LETTER IN THE WORD STRAWBERRY AND COUNT THE LETTERS R
@michelians1148
@michelians1148 2 ай бұрын
Just as likely to answer wrongly.
@RFC3514
@RFC3514 2 ай бұрын
ChatGPT is not wrong. "Strawberry" *does* contain 2 Rs. It contains a _third_ R as well, but it's impossible to contain three Rs without _also_ containing two Rs.
@DoNhatMinhhh
@DoNhatMinhhh 2 ай бұрын
Strawberry is spelled "Strô,berē" and "Strô,berē" only contain 2 Rs, if you want chat GPT to say there are 3 Rs you need to ask it: "How many R are in the word Strawberry, not the spelling of Strawberry"
@Anth230
@Anth230 2 ай бұрын
It took me like three sessions to finally get it ro admit the word had three R's. I told it im going to ask it tomorrow and see if it remembers.. 😂
@NanoGirlPower
@NanoGirlPower 2 ай бұрын
@@Anth230 hahaha let me know what it says tomorrow!
@Anth230
@Anth230 2 ай бұрын
@@NanoGirlPower it forgot it a few hours later. But the good news is it was easier to convince the second time. It apparently remembers it across all platforms for a bit....but then reverts back to its old shenanigans... 😂
@theunknownunknowns256
@theunknownunknowns256 5 ай бұрын
So what we need is a second AI that can generate simple "strawberry" like questions that we can use to see if another AI is worthy. Problem solved... not getting complicated at all. But seriously lets confine it Exurb1a style before it gets away on us.
@zekeriya84
@zekeriya84 Ай бұрын
AI Needs more nuclear power and cooling towers for improvment. We just need to add more fuel. 🙃
@andrewhall6145
@andrewhall6145 2 ай бұрын
I guess it's not that hard. Copilot knows the answer.
@PoorJonathon
@PoorJonathon 2 ай бұрын
ChatGPT counted correctly on strawberries because the "ies" creates the third R apparently?!? The word "strawberries" has one more "R" than "strawberry" because it is the plural form of "strawberry." In "strawberry," there are two "R"s: one in the middle ("strawberry") and one towards the end. When the word becomes plural, an "e" and an "s" are added at the end, forming "strawberries." The added "ies" creates the third "R."
@NanoGirlPower
@NanoGirlPower 2 ай бұрын
@@PoorJonathon oh well that makes total sense 🤷🏻‍♀️
@drsiigabb9935
@drsiigabb9935 2 ай бұрын
So if I was going to offer you $100 dollars for each 'r' in the word strawberry, you'd happily except only $200, instead of $300?
@PoorJonathon
@PoorJonathon 2 ай бұрын
@@drsiigabb9935 Just quoting what it told me, wasn't putting any sort of monetary value on that answer.
@TaxCattle4CorruptDeepState
@TaxCattle4CorruptDeepState 2 ай бұрын
This is due to the delays in Nvidia's Blackwell chip. When shipping of the 70k chip resumes at expected quantities Blackwell will indeed have 3 "l"s instead of 2. In the mean time please keep buying the stock at 40x sales while the insiders sell ASAP. In this way you can transfer your lifetime store of productivity to their bank accounts.
When ChatGPT is confidently wrong
7:44
Pluralsight
Рет қаралды 11 М.
There's Something Weird About ChatGPT o1 Use Cases...
21:05
Matthew Berman
Рет қаралды 81 М.
Увеличили моцареллу для @Lorenzo.bagnati
00:48
Кушать Хочу
Рет қаралды 7 МЛН
The Ultimate Sausage Prank! Watch Their Reactions 😂🌭 #Unexpected
00:17
La La Life Shorts
Рет қаралды 7 МЛН
Happy birthday to you by Secret Vlog
00:12
Secret Vlog
Рет қаралды 6 МЛН
o1-Preview: 11 STUNNING Use Cases
23:11
TheAIGRID
Рет қаралды 46 М.
How many R's in Strawberry? ChatGPT Flaws
6:48
JerseyITguy
Рет қаралды 51
9 incredible AI apps that changed my life forever
16:29
Silicon Valley Girl
Рет қаралды 339 М.
Claude 3.5 Sonnet vs GPT-4o: Side-by-Side Tests
25:10
Patrick Storm
Рет қаралды 129 М.
OpenAI's O1 (Strawberry) AI: Time to Think = Ability to Reason
12:15
Top Minds in AI Explain What’s Coming After GPT-4o | EP #130
25:30
Peter H. Diamandis
Рет қаралды 178 М.
26 Incredible Use Cases for the New GPT-4o
21:58
The AI Advantage
Рет қаралды 853 М.
Has Generative AI Already Peaked? - Computerphile
12:48
Computerphile
Рет қаралды 1 МЛН