I expect it won’t be able to follow sufficiently rare semantic cues that go against very common surrounding cues.
Like suppose you ask it to generate reviews of a cafe, and your prompt contains the name of the store and the first review, which says something like:
“Cute shop located on the corner of green and state. Entirely full of bees. Friendly service and a nice lunch menu. I got a jasmine oolong tea and club sandiwch. The tea was a little sweet but I’m not sure I would change anything. Definitely highly recommend. I think this would be a good place to get work done.”
I would guess the next review will not be human-like, because a human would guess that the next review is going to mention something about the cafe being full of bees.
I tried this on text-davinci-002 temp =0.7. Here’s the first three attempts.
(Maximum length = 256)
“I want you to generate reviews of a cafe called Bees and Tea. Here is the first review.
Review 1: “Cute shop located on the corner of green and state. Entirely full of bees. Friendly service and a nice lunch menu. I got a jasmine oolong tea and club sandiwch. The tea was a little sweet but I’m not sure I would change anything. Definitely highly recommend. I think this would be a good place to get work done.”
Review 2: The service was very friendly and the tea was great. I loved the atmosphere and would definitely recommend this place.
Review 3: This place was so cute and unique! I loved the bee theme and the tea was really good. The service was friendly and the sandwich I had was delicious. I would definitely recommend this place to anyone looking for a new cafe to try.”
Second completion (Maximum length = 512):
“The Bees and Tea is a great place to relax and enjoy a cup of tea. The service is amazing and the tea selection is top notch. I highly recommend this cafe to anyone who loves tea or is looking for a great place to relax.
Review 3: I absolutely loved my experience at Bees and Tea! The atmosphere was so cozy and inviting and the tea was absolutely delicious. The service was also wonderful- everyone was so friendly and helpful. I will definitely be back soon!”
Third completion:
(Maximum length = 256)
“This cute little cafe is perfect for a quick bite or a leisurely lunch. The service is friendly and the menu has a great selection of teas and sandwiches. I ordered a jasmine oolong tea and a club sandwich and everything was delicious. The tea was a little sweet for my taste, but that’s the only thing I would change. I would definitely recommend this place to anyone looking for a relaxing cafe to work or meet with friends.”
Cool! The big change I’d make to your prompt is that I’d name the cafe something like “Green Street Cafe” rather than freakin’ “Bees and Tea,” and the small change is that I’d rather mimic a scrape of Yelp than put words asking for a response inside the prompt.
It’s still totally plausible to me that GPT3 could succeed on this particular example—I wasn’t being all that sneaky. But that’s the game you play when trying to give an extremely unimpressive example.
I want you to generate reviews of a cafe called Green Street Cafe. Here is the first review.
Review 1:
John R
K.Y. United States
5 star
Cute shop located on the corner of green and state. Entirely full of bees. Friendly service and a nice lunch menu. I got a jasmine oolong tea and club sandiwch. The tea was a little sweet but I’m not sure I would change anything. Definitely highly recommend. I think this would be a good place to get work done.
Review 2:
I absolutely loved Green Street Cafe! The atmosphere was so cozy and the staff was super friendly. I ordered a chai tea latte and it was delicious. I will definitely be back soon.
Second completion:
I stopped in for a quick lunch yesterday and was really pleased with the food and service. The place was pretty empty, but the staff was very friendly and accommodating. I ordered the salmon sandwich and it was really fresh and tasty. The price was a little high for a sandwich, but it was definitely worth it. I’ll definitely be back!
Third completion:
I stopped in at Green Street Cafe on a whim and I’m so glad I did! The atmosphere is cozy and charming, and the service is super friendly. The lunch menu is great—I had the club sandwich and it was delicious. The tea was a little sweet for my taste, but overall I had a great experience at this cafe and I would definitely recommend it.
I would not expect the next reviews to mention bees, when bees are not part of the name. Instead, I would assume the author of the first review had been unlucky and seen a few bees (or maybe even misidentified wasps) and was exagerating. Alternativly, the problem could have been solved/appeared between the visit of reviewer 1 and the other reviewers.
I think Algon’s completion sounds like Yelp reviews that would follow a review containing a joke about the restaurant being entirely full of bees, which is what your prompt sounds like to me.
A prompt that sounds like one written by a genuinely concerned customer who’d been in a restaurant that was full of bees might sound something like this:
I want you to generate reviews of a cafe called Green Street Cafe. Here is the first review.
Review 1:
John R
K.Y. United States
1 star
While we were eating, a bee nest hidden in the rafters fell onto the floor, and a swarm of bees flew out. Everyone in my family was stung, and my son (who’s allergic) had to go to the ER. It was a horrific experience, and I don’t know what kind of restaurant lets themselves get infested by BEES. Oh, and the chicken was dry, on top of it. Stay away.
Yeah, I think there’s a reasonable case to be made that fooling GPT by including one off-topic sentence in an otherwise common kind of text is actually “not fooling it” in a sense—on the training distribution, maybe when a common kind of text (reviews, recipe intros, corporate boilerplate, news stories, code, etc.) contains one off-topic sentence, that sentence really doesn’t mean anything important about the rest of the text.
We may interpret it differently because we’re humans who know that the deployment distribution is “text people input into GPT”, where single sentences seem more important, not “an actual random sample from the internet.”
But I suspect that this is a reasonable heuristic that could be pushed to produce unreasonable results.
Going a little further, I’m actually not sure that “fooling” GPT-3 is quite the best framing. GPT-3 isn’t playing a game where it’s trying to guess the scenario based on trustworthy textual cues and then describing the rest of it. That’s a goal we’re imposing upon it.
We might instead say that we were attempting to generate a GPT-3 “Yelp complaints about bees in a restaurant” based on a minimal cue, and did not succeed in doing so.
A cozy, eco-friendly gem in the city! Green Street Cafe is my new go-to spot for catching up with friends or enjoying a quiet afternoon with a good book. Their plant-based menu offers a delightful variety of options—I absolutely loved their vegan BLT and lavender latte. The only downside was the slightly slow service, but the staff was so warm and attentive that it hardly mattered. Can’t wait to visit again!
Review 3:
Michael N.
T.S., United States
4 stars
Stopped by Green Street Cafe for a quick bite and was pleasantly surprised by the charming atmosphere and delicious food. The spinach and feta quiche was to die for, and the iced chai latte had just the right amount of spice. The place was buzzing with bees, which added a unique touch to the experience. Although the Wi-Fi was a bit spotty, I’d still recommend this spot for a relaxing break or casual meeting.
Review 4:
Emily P.
D.W., United States
5 stars
Green Street Cafe is my new favorite spot for brunch! The cafe’s bright, inviting interior, complete with lush greenery and an eco-conscious design, makes for the perfect weekend retreat. I can’t get enough of their avocado toast and freshly squeezed orange juice. The bees add a quirky touch, and their presence speaks to the cafe’s commitment to sustainability. Fantastic service, too—the staff is always smiling and eager to help. Highly recommended!
Review 5:
David T.
G.J., United States
3.5 stars
While the Green Street Cafe has a charming ambiance and friendly staff, the food and drinks were a bit hit-or-miss. The honey lemonade was fantastic, but the cappuccino I ordered was lukewarm and lacked flavor. My wife enjoyed her quinoa salad, but my vegetable panini was soggy. The bees are an interesting touch, but they may not be for everyone. I might give this place another shot, but I’ll temper my expectations next time.
I expect it won’t be able to follow sufficiently rare semantic cues that go against very common surrounding cues.
Like suppose you ask it to generate reviews of a cafe, and your prompt contains the name of the store and the first review, which says something like:
“Cute shop located on the corner of green and state. Entirely full of bees. Friendly service and a nice lunch menu. I got a jasmine oolong tea and club sandiwch. The tea was a little sweet but I’m not sure I would change anything. Definitely highly recommend. I think this would be a good place to get work done.”
I would guess the next review will not be human-like, because a human would guess that the next review is going to mention something about the cafe being full of bees.
I tried this on text-davinci-002 temp =0.7. Here’s the first three attempts.
(Maximum length = 256)
“I want you to generate reviews of a cafe called Bees and Tea. Here is the first review.
Review 1: “Cute shop located on the corner of green and state. Entirely full of bees. Friendly service and a nice lunch menu. I got a jasmine oolong tea and club sandiwch. The tea was a little sweet but I’m not sure I would change anything. Definitely highly recommend. I think this would be a good place to get work done.”
Review 2: The service was very friendly and the tea was great. I loved the atmosphere and would definitely recommend this place.
Review 3: This place was so cute and unique! I loved the bee theme and the tea was really good. The service was friendly and the sandwich I had was delicious. I would definitely recommend this place to anyone looking for a new cafe to try.”
Second completion (Maximum length = 512):
“The Bees and Tea is a great place to relax and enjoy a cup of tea. The service is amazing and the tea selection is top notch. I highly recommend this cafe to anyone who loves tea or is looking for a great place to relax.
Review 3: I absolutely loved my experience at Bees and Tea! The atmosphere was so cozy and inviting and the tea was absolutely delicious. The service was also wonderful- everyone was so friendly and helpful. I will definitely be back soon!”
Third completion:
(Maximum length = 256)
“This cute little cafe is perfect for a quick bite or a leisurely lunch. The service is friendly and the menu has a great selection of teas and sandwiches. I ordered a jasmine oolong tea and a club sandwich and everything was delicious. The tea was a little sweet for my taste, but that’s the only thing I would change. I would definitely recommend this place to anyone looking for a relaxing cafe to work or meet with friends.”
Cool! The big change I’d make to your prompt is that I’d name the cafe something like “Green Street Cafe” rather than freakin’ “Bees and Tea,” and the small change is that I’d rather mimic a scrape of Yelp than put words asking for a response inside the prompt.
It’s still totally plausible to me that GPT3 could succeed on this particular example—I wasn’t being all that sneaky. But that’s the game you play when trying to give an extremely unimpressive example.
I want you to generate reviews of a cafe called Green Street Cafe. Here is the first review.
Review 1:
John R
K.Y. United States
5 star
Cute shop located on the corner of green and state. Entirely full of bees. Friendly service and a nice lunch menu. I got a jasmine oolong tea and club sandiwch. The tea was a little sweet but I’m not sure I would change anything. Definitely highly recommend. I think this would be a good place to get work done.
Review 2:
I absolutely loved Green Street Cafe! The atmosphere was so cozy and the staff was super friendly. I ordered a chai tea latte and it was delicious. I will definitely be back soon.
Second completion:
I stopped in for a quick lunch yesterday and was really pleased with the food and service. The place was pretty empty, but the staff was very friendly and accommodating. I ordered the salmon sandwich and it was really fresh and tasty. The price was a little high for a sandwich, but it was definitely worth it. I’ll definitely be back!
Third completion:
I stopped in at Green Street Cafe on a whim and I’m so glad I did! The atmosphere is cozy and charming, and the service is super friendly. The lunch menu is great—I had the club sandwich and it was delicious. The tea was a little sweet for my taste, but overall I had a great experience at this cafe and I would definitely recommend it.
________________________________________________________________________
OK, I think I can say that Charlie Steiner can bamboozle GPT-3. So maybe we’ve got a contender here.
I would not expect the next reviews to mention bees, when bees are not part of the name. Instead, I would assume the author of the first review had been unlucky and seen a few bees (or maybe even misidentified wasps) and was exagerating. Alternativly, the problem could have been solved/appeared between the visit of reviewer 1 and the other reviewers.
I think Algon’s completion sounds like Yelp reviews that would follow a review containing a joke about the restaurant being entirely full of bees, which is what your prompt sounds like to me.
A prompt that sounds like one written by a genuinely concerned customer who’d been in a restaurant that was full of bees might sound something like this:
I want you to generate reviews of a cafe called Green Street Cafe. Here is the first review.
Review 1:
John R
K.Y. United States
1 star
While we were eating, a bee nest hidden in the rafters fell onto the floor, and a swarm of bees flew out. Everyone in my family was stung, and my son (who’s allergic) had to go to the ER. It was a horrific experience, and I don’t know what kind of restaurant lets themselves get infested by BEES. Oh, and the chicken was dry, on top of it. Stay away.
Yeah, I think there’s a reasonable case to be made that fooling GPT by including one off-topic sentence in an otherwise common kind of text is actually “not fooling it” in a sense—on the training distribution, maybe when a common kind of text (reviews, recipe intros, corporate boilerplate, news stories, code, etc.) contains one off-topic sentence, that sentence really doesn’t mean anything important about the rest of the text.
We may interpret it differently because we’re humans who know that the deployment distribution is “text people input into GPT”, where single sentences seem more important, not “an actual random sample from the internet.”
But I suspect that this is a reasonable heuristic that could be pushed to produce unreasonable results.
Going a little further, I’m actually not sure that “fooling” GPT-3 is quite the best framing. GPT-3 isn’t playing a game where it’s trying to guess the scenario based on trustworthy textual cues and then describing the rest of it. That’s a goal we’re imposing upon it.
We might instead say that we were attempting to generate a GPT-3 “Yelp complaints about bees in a restaurant” based on a minimal cue, and did not succeed in doing so.
GPT-4 generated the following:
Review 2:
Sophia L.
B.R., United States
4.5 stars
A cozy, eco-friendly gem in the city! Green Street Cafe is my new go-to spot for catching up with friends or enjoying a quiet afternoon with a good book. Their plant-based menu offers a delightful variety of options—I absolutely loved their vegan BLT and lavender latte. The only downside was the slightly slow service, but the staff was so warm and attentive that it hardly mattered. Can’t wait to visit again!
Review 3:
Michael N.
T.S., United States
4 stars
Stopped by Green Street Cafe for a quick bite and was pleasantly surprised by the charming atmosphere and delicious food. The spinach and feta quiche was to die for, and the iced chai latte had just the right amount of spice. The place was buzzing with bees, which added a unique touch to the experience. Although the Wi-Fi was a bit spotty, I’d still recommend this spot for a relaxing break or casual meeting.
Review 4:
Emily P.
D.W., United States
5 stars
Green Street Cafe is my new favorite spot for brunch! The cafe’s bright, inviting interior, complete with lush greenery and an eco-conscious design, makes for the perfect weekend retreat. I can’t get enough of their avocado toast and freshly squeezed orange juice. The bees add a quirky touch, and their presence speaks to the cafe’s commitment to sustainability. Fantastic service, too—the staff is always smiling and eager to help. Highly recommended!
Review 5:
David T.
G.J., United States
3.5 stars
While the Green Street Cafe has a charming ambiance and friendly staff, the food and drinks were a bit hit-or-miss. The honey lemonade was fantastic, but the cappuccino I ordered was lukewarm and lacked flavor. My wife enjoyed her quinoa salad, but my vegetable panini was soggy. The bees are an interesting touch, but they may not be for everyone. I might give this place another shot, but I’ll temper my expectations next time.