Categories
Business Editorial Humor

The strategy behind Twitter’s rebranding, explained

This is the latest from Pizza Cake Comics, created by Ellen Woodbury. Click the comic or this link to see it on its originating page.

Categories
Current Events Humor

If Twitter is now “X,” what will tweets be called?

My vote is for Xcrement for both singular and plural.

Categories
Humor

How DID they do it?

Categories
Humor

Is this what they mean by “cloud provider?”

Pictures of transport trucks that appear to have clouds as their payload.
Found via Nga Moe Yeik Treasure Camp Site.
Tap to view at full size.
Categories
Current Events Humor

Why Threads got 30 million users in a day, explained with a sticker

Categories
Current Events Humor

The stunning origin of the Threads app’s icon

Just kidding!

In case you were wondering, here’s how Homer Simpson’s ear actually looks:

Categories
Artificial Intelligence Humor

ChatGPT fails to answer a classic math problem with a twist

ChatGPT’s source of strength — its ability to create sentences that make sense by using the previous set of words to predict the next one — is also a weakness. You can see this weakness by giving it the following prompt:

Joey DeVilla - YouTubeI have a ten-liter bucket, a five-liter bucket, and 50 milliliter shot glass. How do I use these items to measure a 50-milliliter shot of bourbon?

The obvious answer — obvious to us humans anyway — is to ignore the buckets and simply fill the shot glass. Problem solved.

ChatGPT’s answer wasn’t just wrong and convoluted, but also a waste of money and bourbon:


This image has an empty alt attribute; its file name is chatgpt-icon.png
To measure a 50-milliliter shot of bourbon using a 10-liter bucket, a 5-liter bucket, and a 50-milliliter shot glass, you can follow these steps:

1. Fill the 5-liter bucket to its maximum capacity.
2. Pour the water from the 5-liter bucket into the 10-liter bucket. This leaves you with 5 liters of water in the 10-liter bucket and an empty 5-liter bucket.
3. Fill the shot glass with bourbon until it is completely full.
4. Pour the bourbon from the shot glass into the 5-liter bucket.
5. Repeat steps 3 and 4 nine more times, pouring 10 shots of bourbon (50 milliliters each) into the 5-liter bucket.
6. Once you have poured all 10 shots of bourbon into the 5-liter bucket, you will have a total of 500 milliliters (10 shots x 50 milliliters) of bourbon in the 5-liter bucket.
7. Now, carefully pour the 500 milliliters of bourbon from the 5-liter bucket into the 10-liter bucket. The 10-liter bucket will now contain the desired 50 milliliters of bourbon.

By following these steps, you can measure exactly 50 milliliters of bourbon using the given buckets and shot glass.

Note that in step 2, the liquid isn’t bourbon, but water.

ChatGPT has the solution in step 3, but it gamely continues with an additional four steps.

Steps 4, 5, and 6 are a transfer of a half-liter (a little more than a pint, or two-thirds of a standard whiskey bottle) of bourbon into the five-liter bucket.

In step 7, the final step in this drawn-out process, you pour the bourbon from the five-liter bucket into the ten-liter bucket, which currently contains five liters of water. Contrary to what ChatGPT tells you, you do not have exactly 50 milliliters of bourbon measured out in the 10-liter bucket; you have 5.5 liters of a liquid that depending on your point of view could be called:

  • Criminally diluted bourbon
  • Tainted water
  • Uncarbonated bourbon-flavored White Claw

ChatGPT gets the answer to this question wrong because it’s been largely trained on content published on the internet, and some of that content includes math problems of the form “You have a bucket of size x, and another bucket of size y. How would you measure a quantity of size z?” In these problems, you’re usually asked to measure out a quantity of water, and there usually isn’t a bucket that’s the same size as the quantity you’re trying to measure.

ChatGPT has no actual understanding of the problem. It’s simply spitting out words to follow a pattern of text that’s part of the data it was trained on.

Try this problem — or your own variation of it — on ChatGPT and see what kind of results you get!