But what about, "What is the sum of the digits of 15683615?"
Bard says:
The sum of the digits of 15683615 is 28.
Here's how I got the answer:
1 + 5 + 6 + 8 + 3 + 6 + 1 + 5 = 28
====
I don't think this is ready for prime time.
But what about, "What is the sum of the digits of 15683615?"
Bard says:
The sum of the digits of 15683615 is 28.
Here's how I got the answer:
1 + 5 + 6 + 8 + 3 + 6 + 1 + 5 = 28
====
I don't think this is ready for prime time.
To find the sum of the digits of a number, you add together all the individual digits. In the case of the number 15683615, the sum of its digits would be:
1 + 5 + 6 + 8 + 3 + 6 + 1 + 5 = 35
Therefore, the sum of the digits of 15683615 is 35.
====
Good job ChatGPT. This sort of “near miss” for Bard has been my experience the entire time I’ve compared Bard and ChatGPT.
In the most hilarious example, I asked both to reword an email to someone named “Helena” to explain how I’ve been busy and did not return her email. I included her prompt for context, including her asking if I was on vacation. ChatGPT did a good job of adjusting my wording to be better understood by a non native English speaker and used her prompt appropriately. Bard spun a story about how I was vacationing with my non-existent children in Helena Montana.
Bard just isn’t there yet.
To find the prime factors of 15,683,615, we can use a process called prime factorization. We divide the number by prime numbers until it can no longer be divided evenly. Here's the step-by-step process:
We start by dividing 15,683,615 by the smallest prime number, which is 2. However, 15,683,615 is an odd number and not divisible by 2.
Next, we try the next prime number, 3. If we divide 15,683,615 by 3, we get 5,227,871. Again, this is an odd number.
We continue with the next prime number, 5. Dividing 15,683,615 by 5 gives us 3,136,723. Still an odd number.
Moving on to the next prime number, 7. Dividing 15,683,615 by 7 yields 2,240,516. Again, this is an odd number.
We try the next prime number, 11. Dividing 15,683,615 by 11 gives us 1,425,783. Still an odd number.
Next, we try the prime number 13. Dividing 15,683,615 by 13 yields 1,205,659. This is an odd number.
Continuing with the next prime number, 17. Dividing 15,683,615 by 17 gives us 920,755. Still an odd number.
We try the prime number 19. Dividing 15,683,615 by 19 yields 823,035. This is an odd number.
The next prime number is 23. Dividing 15,683,615 by 23 gives us 680,563. Still an odd number.
Finally, we try the prime number 29. Dividing 15,683,615 by 29 yields 539,475, which is divisible by 5.
Therefore, the prime factors of 15,683,615 are 3, 5, 5, 7, 11, 13, 17, 19, 23, and 29.
"Create a map with tect using only the letters B,W,S. The map should be a 20 line by 20 colum text . Each line should contain only B,W or S letters were W are walls, B is blank/background space and S represent "stairs" to outside of the room...."
The query was a it longer with more specs.
Neither ChatGPT nor Bard could give me a good answer. They used other letters , they made 21 or 19 chars lines. They made 5 or 6 line maps. They basically made a mess.
That's my current test for reasoning, analysis and intelligence for these things.
Took me an hour to figure out why it didn’t work.
O != 0
You're also right about hallucinating the execution.
I was testing PLAM-2 today and I noticed it's quite a lot more resistant to sycophancy attacks...
draft 1: The sum of the digits of 15683615 is 27.
draft 2: The sum of the digits of 15683615 is 26.
draft 3: The sum of the digits of 15683615 is 30.
Do we know if it has actually learned how to do the operation?
Like, regardless of how it works under the hood, I as an end user just want a useful result. Even if ChatGPT is "cheating" to accomplish those results, it looks better for the end user.
The continued trickle of disappointing updates to Bard seems to indicate why Google hadn't productized their AI research before OpenAI did.
Feel free to downvote as I'm too tired to post links to recent votes in the play store :)
Sorry for the snark in this post, but I have been less than impressed by google's engineering capability for more than 10 years now. My tolerance to quirks like the one I just posted is, kind of, low.
¹ An authenticator app is a very low bar to mess up