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 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.