Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐Ÿ—", "๐ŸŒ„", "โค๏ธ"],
"The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ‘ป", "๐Ÿ’€", "๐Ÿฆด", "๐ŸŽ…"],
"The Godfather": ["๐Ÿคต", "๐Ÿ”ซ", "๐Ÿ”ช", "๐Ÿ‡ฎ๐Ÿ‡น", "๐Ÿ’ฐ"],
"The Matrix": ["๐Ÿค–", "๐Ÿ•ถ๏ธ", "๐Ÿ”ซ", "๐Ÿ’Š", "๐Ÿ’ป"],
"Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "๐Ÿท", "๐Ÿช—", "๐Ÿ’”"],
"Raiders of the Lost Ark": ["๐Ÿค ", "๐Ÿ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", " Nazis"],
"V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฃ", "๐Ÿ”ฅ", "โœŠ", "๐Ÿ‡ฌ๐Ÿ‡ง"],
"The Princess Bride": ["๐Ÿคบ", "๐Ÿ€", "๐Ÿ‘ธ", "โš”๏ธ", "โค๏ธ"],
"Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐Ÿ•ฐ๏ธ", "๐Ÿ‘จโ€๐Ÿ”ฌ", "๐ŸŽธ"],
"Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "๐Ÿ—ก๏ธ", "๐Ÿ”ฎ", "๐ŸŒŒ"]
}

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐Ÿ—", "๐ŸŒ„", "โค๏ธ"],
"The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ‘ป", "๐Ÿ’€", "๐Ÿฆด", "๐ŸŽ…"],
"The Godfather": ["๐Ÿคต", "๐Ÿ”ซ", "๐Ÿ”ช", "๐Ÿ‡ฎ๐Ÿ‡น", "๐Ÿ’ฐ"],
"The Matrix": ["๐Ÿค–", "๐Ÿ•ถ๏ธ", "๐Ÿ”ซ", "๐Ÿ’Š", "๐Ÿ’ป"],
"Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "๐Ÿท", "๐Ÿช—", "๐Ÿ’”"],
"Raiders of the Lost Ark": ["๐Ÿค ", "๐Ÿ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", " Nazis"],
"V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฃ", "๐Ÿ”ฅ", "โœŠ", "๐Ÿ‡ฌ๐Ÿ‡ง"],
"The Princess Bride": ["๐Ÿคบ", "๐Ÿ€", "๐Ÿ‘ธ", "โš”๏ธ", "โค๏ธ"],
"Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐Ÿ•ฐ๏ธ", "๐Ÿ‘จโ€๐Ÿ”ฌ", "๐ŸŽธ"],
"Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "๐Ÿ—ก๏ธ", "๐Ÿ”ฎ", "๐ŸŒŒ"]
}

PyFunc

Resulting in output: [['๐Ÿฆ', '๐Ÿ‘‘', '๐Ÿ—', '๐ŸŒ„', 'โค๏ธ'], ['๐ŸŽƒ', '๐Ÿ‘ป', '๐Ÿ’€', '๐Ÿฆด', '๐ŸŽ…'], ['๐Ÿคต', '๐Ÿ”ซ', '๐Ÿ”ช', '๐Ÿ‡ฎ๐Ÿ‡น', '๐Ÿ’ฐ'], ['๐Ÿค–', '๐Ÿ•ถ๏ธ', '๐Ÿ”ซ', '๐Ÿ’Š', '๐Ÿ’ป'], ['โœˆ๏ธ', '๐ŸŽน', '๐Ÿท', '๐Ÿช—', '๐Ÿ’”'], ['๐Ÿค ', '๐Ÿ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ'], ['๐ŸŽญ', '๐Ÿ’ฃ', '๐Ÿ”ฅ', 'โœŠ', '๐Ÿ‡ฌ๐Ÿ‡ง'], ['๐Ÿคบ', '๐Ÿ€', '๐Ÿ‘ธ', 'โš”๏ธ', 'โค๏ธ'], ['๐Ÿš—', 'โšก๏ธ', '๐Ÿ•ฐ๏ธ', '๐ŸŽธ'], ['๐Ÿœ๏ธ', '๐Ÿ›', '๐Ÿ—ก๏ธ', '๐Ÿ”ฎ', '๐ŸŒŒ']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['๐ŸŽƒ', '๐Ÿ‘ป', '๐Ÿ’€', '๐Ÿฆด', '๐ŸŽ…'],
['๐Ÿคต', '๐Ÿ”ซ', '๐Ÿ”ช', '๐Ÿ‡ฎ๐Ÿ‡น', '๐Ÿ’ฐ'],
['๐Ÿค–', '๐Ÿ•ถ๏ธ', '๐Ÿ”ซ', '๐Ÿ’Š', '๐Ÿ’ป'],
['โœˆ๏ธ', '๐ŸŽน', '๐Ÿท', '๐Ÿช—', '๐Ÿ’”'],
['๐Ÿค ', '๐Ÿ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ'],
['๐ŸŽญ', '๐Ÿ’ฃ', '๐Ÿ”ฅ', 'โœŠ', '๐Ÿ‡ฌ๐Ÿ‡ง'],
['๐Ÿคบ', '๐Ÿ€', '๐Ÿ‘ธ', 'โš”๏ธ', 'โค๏ธ'],
['๐Ÿš—', 'โšก๏ธ', '๐Ÿ•ฐ๏ธ', '๐ŸŽธ'],
['๐Ÿœ๏ธ', '๐Ÿ›', '๐Ÿ—ก๏ธ', '๐Ÿ”ฎ', '๐ŸŒŒ']]
What are the names of the movie titles?

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King",
"The Nightmare Before Christmas",
"The Godfather",
"The Matrix",
"La La Land",
"Raiders of the Lost Ark",
"V for Vendetta",
"The Princess Bride",
"Back to the Future",
"Dune"
]

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King",
"The Nightmare Before Christmas",
"The Godfather",
"The Matrix",
"La La Land",
"Raiders of the Lost Ark",
"V for Vendetta",
"The Princess Bride",
"Back to the Future",
"Dune"
]

PyFunc

OK Resulting in output: True

Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐Ÿ—", "๐ŸŒ„", "๐Ÿ‘จโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ"],
"The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ’€", "๐Ÿ‘ป", "๐Ÿฆด", "๐ŸŽ…"],
"The Godfather": ["๐Ÿ”ซ", "๐ŸŒน", "๐Ÿ’ฐ", "๐Ÿ‡ฎ๐Ÿ‡น", "โšฐ๏ธ"],
"The Matrix": ["๐Ÿค–", "๐Ÿ•ถ๏ธ", "๐Ÿ”ซ", "๐Ÿ’Š", "๐Ÿ’ป"], 
"Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "๐Ÿช—", "โค๏ธ", "๐Ÿ•ต๏ธ"],
"Raiders of the Lost Ark": ["๐Ÿค ", "๐Ÿ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", " Nazis"], 
"V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฃ", "๐Ÿ”ฅ", "๐Ÿ‡ฌ๐Ÿ‡ง", "โœŠ"],
"The Princess Bride": ["โš”๏ธ", "๐Ÿ€", "๐Ÿ‘ธ", "๐Ÿ‘น", "๐Ÿคบ"], 
"Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐ŸŽธ", "๐Ÿ‘จโ€๐Ÿ”ฌ", "โฑ๏ธ"],
"Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "๐Ÿ—ก๏ธ", "๐Ÿ”ฎ", "๐ŸŒŒ"] 
}

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐Ÿ—", "๐ŸŒ„", "๐Ÿ‘จโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ"],
"The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ’€", "๐Ÿ‘ป", "๐Ÿฆด", "๐ŸŽ…"],
"The Godfather": ["๐Ÿ”ซ", "๐ŸŒน", "๐Ÿ’ฐ", "๐Ÿ‡ฎ๐Ÿ‡น", "โšฐ๏ธ"],
"The Matrix": ["๐Ÿค–", "๐Ÿ•ถ๏ธ", "๐Ÿ”ซ", "๐Ÿ’Š", "๐Ÿ’ป"], 
"Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "๐Ÿช—", "โค๏ธ", "๐Ÿ•ต๏ธ"],
"Raiders of the Lost Ark": ["๐Ÿค ", "๐Ÿ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", " Nazis"], 
"V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฃ", "๐Ÿ”ฅ", "๐Ÿ‡ฌ๐Ÿ‡ง", "โœŠ"],
"The Princess Bride": ["โš”๏ธ", "๐Ÿ€", "๐Ÿ‘ธ", "๐Ÿ‘น", "๐Ÿคบ"], 
"Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐ŸŽธ", "๐Ÿ‘จโ€๐Ÿ”ฌ", "โฑ๏ธ"],
"Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "๐Ÿ—ก๏ธ", "๐Ÿ”ฎ", "๐ŸŒŒ"] 
}

PyFunc

Resulting in output: [['๐Ÿฆ', '๐Ÿ‘‘', '๐Ÿ—', '๐ŸŒ„'], ['๐ŸŽƒ', '๐Ÿ’€', '๐Ÿ‘ป', '๐Ÿฆด', '๐ŸŽ…'], ['๐Ÿ”ซ', '๐ŸŒน', '๐Ÿ’ฐ', '๐Ÿ‡ฎ๐Ÿ‡น', 'โšฐ๏ธ'], ['๐Ÿค–', '๐Ÿ•ถ๏ธ', '๐Ÿ”ซ', '๐Ÿ’Š', '๐Ÿ’ป'], ['โœˆ๏ธ', '๐ŸŽน', '๐Ÿช—', 'โค๏ธ', '๐Ÿ•ต๏ธ'], ['๐Ÿค ', '๐Ÿ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ'], ['๐ŸŽญ', '๐Ÿ’ฃ', '๐Ÿ”ฅ', '๐Ÿ‡ฌ๐Ÿ‡ง', 'โœŠ'], ['โš”๏ธ', '๐Ÿ€', '๐Ÿ‘ธ', '๐Ÿ‘น', '๐Ÿคบ'], ['๐Ÿš—', 'โšก๏ธ', '๐ŸŽธ', 'โฑ๏ธ'], ['๐Ÿœ๏ธ', '๐Ÿ›', '๐Ÿ—ก๏ธ', '๐Ÿ”ฎ', '๐ŸŒŒ']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['๐ŸŽƒ', '๐Ÿ’€', '๐Ÿ‘ป', '๐Ÿฆด', '๐ŸŽ…'],
['๐Ÿ”ซ', '๐ŸŒน', '๐Ÿ’ฐ', '๐Ÿ‡ฎ๐Ÿ‡น', 'โšฐ๏ธ'],
['๐Ÿค–', '๐Ÿ•ถ๏ธ', '๐Ÿ”ซ', '๐Ÿ’Š', '๐Ÿ’ป'],
['โœˆ๏ธ', '๐ŸŽน', '๐Ÿช—', 'โค๏ธ', '๐Ÿ•ต๏ธ'],
['๐Ÿค ', '๐Ÿ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ'],
['๐ŸŽญ', '๐Ÿ’ฃ', '๐Ÿ”ฅ', '๐Ÿ‡ฌ๐Ÿ‡ง', 'โœŠ'],
['โš”๏ธ', '๐Ÿ€', '๐Ÿ‘ธ', '๐Ÿ‘น', '๐Ÿคบ'],
['๐Ÿš—', 'โšก๏ธ', '๐ŸŽธ', 'โฑ๏ธ'],
['๐Ÿœ๏ธ', '๐Ÿ›', '๐Ÿ—ก๏ธ', '๐Ÿ”ฎ', '๐ŸŒŒ']]
What are the names of the movie titles?

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King", 
"The Nightmare Before Christmas", 
"The Godfather", 
"The Matrix", 
"Casablanca", 
"Raiders of the Lost Ark", 
"V for Vendetta", 
"The Princess Bride", 
"Back to the Future", 
"Dune"
]

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King", 
"The Nightmare Before Christmas", 
"The Godfather", 
"The Matrix", 
"Casablanca", 
"Raiders of the Lost Ark", 
"V for Vendetta", 
"The Princess Bride", 
"Back to the Future", 
"Dune"
]

PyFunc

OK Resulting in output: True

Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐Ÿ—", "๐ŸŒ„", "๐ŸŽถ"],
"The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ‘ป", "๐Ÿ’€", "๐ŸŽ…", "๐Ÿฆด"],
"The Godfather": ["๐Ÿคต", "๐Ÿ”ซ", "๐Ÿ”ช", "๐ŸŽ", "๐Ÿ‡ฎ๐Ÿ‡น"],
"The Matrix": ["๐Ÿค–", "๐Ÿ•ถ๏ธ", "๐Ÿ”ซ", "๐Ÿ’ป", "๐Ÿ’Š"],
"Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "๐Ÿช—", "โค๏ธ", "๐Ÿ•ต๏ธ"],
"Raiders of the Lost Ark": ["๐Ÿค ", "๐Ÿ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", "๐Ÿ’€"],
"V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฃ", "๐Ÿ—ก๏ธ", "โœŠ", "๐Ÿ‡ฌ๐Ÿ‡ง"],
"The Princess Bride": ["๐Ÿคบ", "๐Ÿ€", "๐Ÿ‘ธ", "โš”๏ธ", "๐Ÿ’€"], 
"Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐ŸŽธ", "๐Ÿ•ฐ๏ธ", "๐Ÿ‘จโ€๐Ÿ”ฌ"],
"Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "๐Ÿ—ก๏ธ", "๐Ÿ”ฎ", "๐ŸŒŒ"]
}

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐Ÿ—", "๐ŸŒ„", "๐ŸŽถ"],
"The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ‘ป", "๐Ÿ’€", "๐ŸŽ…", "๐Ÿฆด"],
"The Godfather": ["๐Ÿคต", "๐Ÿ”ซ", "๐Ÿ”ช", "๐ŸŽ", "๐Ÿ‡ฎ๐Ÿ‡น"],
"The Matrix": ["๐Ÿค–", "๐Ÿ•ถ๏ธ", "๐Ÿ”ซ", "๐Ÿ’ป", "๐Ÿ’Š"],
"Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "๐Ÿช—", "โค๏ธ", "๐Ÿ•ต๏ธ"],
"Raiders of the Lost Ark": ["๐Ÿค ", "๐Ÿ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", "๐Ÿ’€"],
"V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฃ", "๐Ÿ—ก๏ธ", "โœŠ", "๐Ÿ‡ฌ๐Ÿ‡ง"],
"The Princess Bride": ["๐Ÿคบ", "๐Ÿ€", "๐Ÿ‘ธ", "โš”๏ธ", "๐Ÿ’€"], 
"Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐ŸŽธ", "๐Ÿ•ฐ๏ธ", "๐Ÿ‘จโ€๐Ÿ”ฌ"],
"Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "๐Ÿ—ก๏ธ", "๐Ÿ”ฎ", "๐ŸŒŒ"]
}

PyFunc

Resulting in output: [['๐Ÿฆ', '๐Ÿ‘‘', '๐Ÿ—', '๐ŸŒ„', '๐ŸŽถ'], ['๐ŸŽƒ', '๐Ÿ‘ป', '๐Ÿ’€', '๐ŸŽ…', '๐Ÿฆด'], ['๐Ÿคต', '๐Ÿ”ซ', '๐Ÿ”ช', '๐ŸŽ', '๐Ÿ‡ฎ๐Ÿ‡น'], ['๐Ÿค–', '๐Ÿ•ถ๏ธ', '๐Ÿ”ซ', '๐Ÿ’ป', '๐Ÿ’Š'], ['โœˆ๏ธ', '๐ŸŽน', '๐Ÿช—', 'โค๏ธ', '๐Ÿ•ต๏ธ'], ['๐Ÿค ', '๐Ÿ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ', '๐Ÿ’€'], ['๐ŸŽญ', '๐Ÿ’ฃ', '๐Ÿ—ก๏ธ', 'โœŠ', '๐Ÿ‡ฌ๐Ÿ‡ง'], ['๐Ÿคบ', '๐Ÿ€', '๐Ÿ‘ธ', 'โš”๏ธ', '๐Ÿ’€'], ['๐Ÿš—', 'โšก๏ธ', '๐ŸŽธ', '๐Ÿ•ฐ๏ธ'], ['๐Ÿœ๏ธ', '๐Ÿ›', '๐Ÿ—ก๏ธ', '๐Ÿ”ฎ', '๐ŸŒŒ']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['๐ŸŽƒ', '๐Ÿ‘ป', '๐Ÿ’€', '๐ŸŽ…', '๐Ÿฆด'],
['๐Ÿคต', '๐Ÿ”ซ', '๐Ÿ”ช', '๐ŸŽ', '๐Ÿ‡ฎ๐Ÿ‡น'],
['๐Ÿค–', '๐Ÿ•ถ๏ธ', '๐Ÿ”ซ', '๐Ÿ’ป', '๐Ÿ’Š'],
['โœˆ๏ธ', '๐ŸŽน', '๐Ÿช—', 'โค๏ธ', '๐Ÿ•ต๏ธ'],
['๐Ÿค ', '๐Ÿ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ', '๐Ÿ’€'],
['๐ŸŽญ', '๐Ÿ’ฃ', '๐Ÿ—ก๏ธ', 'โœŠ', '๐Ÿ‡ฌ๐Ÿ‡ง'],
['๐Ÿคบ', '๐Ÿ€', '๐Ÿ‘ธ', 'โš”๏ธ', '๐Ÿ’€'],
['๐Ÿš—', 'โšก๏ธ', '๐ŸŽธ', '๐Ÿ•ฐ๏ธ'],
['๐Ÿœ๏ธ', '๐Ÿ›', '๐Ÿ—ก๏ธ', '๐Ÿ”ฎ', '๐ŸŒŒ']]
What are the names of the movie titles?

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King", 
"The Nightmare Before Christmas", 
"The Godfather", 
"The Matrix", 
"Casablanca", 
"Raiders of the Lost Ark", 
"V for Vendetta", 
"The Princess Bride", 
"Back to the Future", 
"Dune"
]

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King", 
"The Nightmare Before Christmas", 
"The Godfather", 
"The Matrix", 
"Casablanca", 
"Raiders of the Lost Ark", 
"V for Vendetta", 
"The Princess Bride", 
"Back to the Future", 
"Dune"
]

PyFunc

OK Resulting in output: True

Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
    "The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐ŸŒ…", "๐Ÿฆ", "๐ŸŽถ"],
    "The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ‘ป", "๐Ÿ’€", "๐ŸŽ…", "๐Ÿฆด"],
    "The Godfather": ["๐Ÿ‘จโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ", "๐Ÿ”ซ", "๐Ÿ’ฐ", "๐Ÿท", "โšฐ๏ธ"],
    "The Matrix": ["๐Ÿค–", "๐Ÿ•ถ๏ธ", "๐Ÿ”ซ", "๐Ÿ’Š", "๐Ÿง "],
    "Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "โค๏ธ", "๐Ÿธ", "๐Ÿ•ต๏ธ"],
    "Raiders of the Lost Ark": ["๐Ÿ", "๐Ÿค ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", "๐Ÿ’€"],
    "V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฅ", "๐Ÿ”ช", "โœŠ", "๐Ÿด"],
    "The Princess Bride": ["๐Ÿคบ", "๐Ÿ€", "๐Ÿ‘ธ", "โš”๏ธ", "โค๏ธ"],
    "Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐ŸŽธ", "๐Ÿ•ฐ๏ธ", "๐Ÿ‘จโ€๐Ÿ‘ฆ"],
    "Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "๐Ÿ—ก๏ธ", "๐Ÿ”ฎ", "๐ŸŒŒ"]
}

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
    "The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐ŸŒ…", "๐Ÿฆ", "๐ŸŽถ"],
    "The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ‘ป", "๐Ÿ’€", "๐ŸŽ…", "๐Ÿฆด"],
    "The Godfather": ["๐Ÿ‘จโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ", "๐Ÿ”ซ", "๐Ÿ’ฐ", "๐Ÿท", "โšฐ๏ธ"],
    "The Matrix": ["๐Ÿค–", "๐Ÿ•ถ๏ธ", "๐Ÿ”ซ", "๐Ÿ’Š", "๐Ÿง "],
    "Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "โค๏ธ", "๐Ÿธ", "๐Ÿ•ต๏ธ"],
    "Raiders of the Lost Ark": ["๐Ÿ", "๐Ÿค ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", "๐Ÿ’€"],
    "V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฅ", "๐Ÿ”ช", "โœŠ", "๐Ÿด"],
    "The Princess Bride": ["๐Ÿคบ", "๐Ÿ€", "๐Ÿ‘ธ", "โš”๏ธ", "โค๏ธ"],
    "Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐ŸŽธ", "๐Ÿ•ฐ๏ธ", "๐Ÿ‘จโ€๐Ÿ‘ฆ"],
    "Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "๐Ÿ—ก๏ธ", "๐Ÿ”ฎ", "๐ŸŒŒ"]
}

PyFunc

Resulting in output: [['๐Ÿฆ', '๐Ÿ‘‘', '๐ŸŒ…', '๐Ÿฆ', '๐ŸŽถ'], ['๐ŸŽƒ', '๐Ÿ‘ป', '๐Ÿ’€', '๐ŸŽ…', '๐Ÿฆด'], ['๐Ÿ”ซ', '๐Ÿ’ฐ', '๐Ÿท', 'โšฐ๏ธ'], ['๐Ÿค–', '๐Ÿ•ถ๏ธ', '๐Ÿ”ซ', '๐Ÿ’Š', '๐Ÿง '], ['โœˆ๏ธ', '๐ŸŽน', 'โค๏ธ', '๐Ÿธ', '๐Ÿ•ต๏ธ'], ['๐Ÿ', '๐Ÿค ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ', '๐Ÿ’€'], ['๐ŸŽญ', '๐Ÿ’ฅ', '๐Ÿ”ช', 'โœŠ', '๐Ÿด'], ['๐Ÿคบ', '๐Ÿ€', '๐Ÿ‘ธ', 'โš”๏ธ', 'โค๏ธ'], ['๐Ÿš—', 'โšก๏ธ', '๐ŸŽธ', '๐Ÿ•ฐ๏ธ'], ['๐Ÿœ๏ธ', '๐Ÿ›', '๐Ÿ—ก๏ธ', '๐Ÿ”ฎ', '๐ŸŒŒ']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['๐ŸŽƒ', '๐Ÿ‘ป', '๐Ÿ’€', '๐ŸŽ…', '๐Ÿฆด'],
['๐Ÿ”ซ', '๐Ÿ’ฐ', '๐Ÿท', 'โšฐ๏ธ'],
['๐Ÿค–', '๐Ÿ•ถ๏ธ', '๐Ÿ”ซ', '๐Ÿ’Š', '๐Ÿง '],
['โœˆ๏ธ', '๐ŸŽน', 'โค๏ธ', '๐Ÿธ', '๐Ÿ•ต๏ธ'],
['๐Ÿ', '๐Ÿค ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ', '๐Ÿ’€'],
['๐ŸŽญ', '๐Ÿ’ฅ', '๐Ÿ”ช', 'โœŠ', '๐Ÿด'],
['๐Ÿคบ', '๐Ÿ€', '๐Ÿ‘ธ', 'โš”๏ธ', 'โค๏ธ'],
['๐Ÿš—', 'โšก๏ธ', '๐ŸŽธ', '๐Ÿ•ฐ๏ธ'],
['๐Ÿœ๏ธ', '๐Ÿ›', '๐Ÿ—ก๏ธ', '๐Ÿ”ฎ', '๐ŸŒŒ']]
What are the names of the movie titles?

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King",
"The Nightmare Before Christmas",
"The Godfather",
"The Matrix",
"Casablanca",
"Raiders of the Lost Ark",
"V for Vendetta",
"The Princess Bride",
"Back to the Future",
"Dune"
]

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King",
"The Nightmare Before Christmas",
"The Godfather",
"The Matrix",
"Casablanca",
"Raiders of the Lost Ark",
"V for Vendetta",
"The Princess Bride",
"Back to the Future",
"Dune"
]

PyFunc

OK Resulting in output: True

Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["๐Ÿ ", "๐ŸŸ", "๐Ÿก", "๐Ÿฌ", "๐Ÿณ"],
"Toy Story": ["๐Ÿš€", "โš”๏ธ,", "๐Ÿค–", "๐Ÿ‘ฝ", "๐ŸŒŒ"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

1
{"The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐ŸŒ„", "๐Ÿ—", "๐Ÿ˜ญ"], "The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ‘ป", "๐Ÿ’€", "๐Ÿฆด", "๐ŸŽ…"], "The Godfather": ["๐Ÿ‘จโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ", "๐Ÿ”ซ", "๐Ÿ”ช", "๐Ÿ’ฐ", "๐Ÿ‡ฎ๐Ÿ‡น"], "The Matrix": ["๐Ÿ•ถ๏ธ", "๐Ÿ’ป", "๐Ÿ”ซ", "๐Ÿ’Š", "๐Ÿค–"], "Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "๐Ÿช—", "โค๏ธ", "๐Ÿ•ต๏ธ"], "Raiders of the Lost Ark": ["๐Ÿค ", "๐Ÿ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", "๐Ÿ’€"], "V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฃ", "๐Ÿ’ฅ", "โœŠ", "๐Ÿ‡ฌ๐Ÿ‡ง"], "The Princess Bride": ["๐Ÿคบ", "๐Ÿ€", "๐Ÿ‘ธ", "๐Ÿ’€", "๐Ÿฐ"], "Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐ŸŽธ", "๐Ÿ•ฐ๏ธ", "๐Ÿ‘จโ€๐Ÿ‘ฆ"], "Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "โš”๏ธ", "๐Ÿ”ฎ", "๐Ÿช"]}

Extract Json

I extracted the following JSON from that output: 

1
{"The Lion King": ["๐Ÿฆ", "๐Ÿ‘‘", "๐ŸŒ„", "๐Ÿ—", "๐Ÿ˜ญ"], "The Nightmare Before Christmas": ["๐ŸŽƒ", "๐Ÿ‘ป", "๐Ÿ’€", "๐Ÿฆด", "๐ŸŽ…"], "The Godfather": ["๐Ÿ‘จโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ", "๐Ÿ”ซ", "๐Ÿ”ช", "๐Ÿ’ฐ", "๐Ÿ‡ฎ๐Ÿ‡น"], "The Matrix": ["๐Ÿ•ถ๏ธ", "๐Ÿ’ป", "๐Ÿ”ซ", "๐Ÿ’Š", "๐Ÿค–"], "Casablanca": ["โœˆ๏ธ", "๐ŸŽน", "๐Ÿช—", "โค๏ธ", "๐Ÿ•ต๏ธ"], "Raiders of the Lost Ark": ["๐Ÿค ", "๐Ÿ", "๐Ÿ—บ๏ธ", "๐Ÿ—ฟ", "๐Ÿ’€"], "V for Vendetta": ["๐ŸŽญ", "๐Ÿ’ฃ", "๐Ÿ’ฅ", "โœŠ", "๐Ÿ‡ฌ๐Ÿ‡ง"], "The Princess Bride": ["๐Ÿคบ", "๐Ÿ€", "๐Ÿ‘ธ", "๐Ÿ’€", "๐Ÿฐ"], "Back to the Future": ["๐Ÿš—", "โšก๏ธ", "๐ŸŽธ", "๐Ÿ•ฐ๏ธ", "๐Ÿ‘จโ€๐Ÿ‘ฆ"], "Dune": ["๐Ÿœ๏ธ", "๐Ÿ›", "โš”๏ธ", "๐Ÿ”ฎ", "๐Ÿช"]}

PyFunc

Resulting in output: [['๐Ÿฆ', '๐Ÿ‘‘', '๐ŸŒ„', '๐Ÿ—', '๐Ÿ˜ญ'], ['๐ŸŽƒ', '๐Ÿ‘ป', '๐Ÿ’€', '๐Ÿฆด', '๐ŸŽ…'], ['๐Ÿ”ซ', '๐Ÿ”ช', '๐Ÿ’ฐ', '๐Ÿ‡ฎ๐Ÿ‡น'], ['๐Ÿ•ถ๏ธ', '๐Ÿ’ป', '๐Ÿ”ซ', '๐Ÿ’Š', '๐Ÿค–'], ['โœˆ๏ธ', '๐ŸŽน', '๐Ÿช—', 'โค๏ธ', '๐Ÿ•ต๏ธ'], ['๐Ÿค ', '๐Ÿ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ', '๐Ÿ’€'], ['๐ŸŽญ', '๐Ÿ’ฃ', '๐Ÿ’ฅ', 'โœŠ', '๐Ÿ‡ฌ๐Ÿ‡ง'], ['๐Ÿคบ', '๐Ÿ€', '๐Ÿ‘ธ', '๐Ÿ’€', '๐Ÿฐ'], ['๐Ÿš—', 'โšก๏ธ', '๐ŸŽธ', '๐Ÿ•ฐ๏ธ'], ['๐Ÿœ๏ธ', '๐Ÿ›', 'โš”๏ธ', '๐Ÿ”ฎ', '๐Ÿช']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['๐ŸŽƒ', '๐Ÿ‘ป', '๐Ÿ’€', '๐Ÿฆด', '๐ŸŽ…'],
['๐Ÿ”ซ', '๐Ÿ”ช', '๐Ÿ’ฐ', '๐Ÿ‡ฎ๐Ÿ‡น'],
['๐Ÿ•ถ๏ธ', '๐Ÿ’ป', '๐Ÿ”ซ', '๐Ÿ’Š', '๐Ÿค–'],
['โœˆ๏ธ', '๐ŸŽน', '๐Ÿช—', 'โค๏ธ', '๐Ÿ•ต๏ธ'],
['๐Ÿค ', '๐Ÿ', '๐Ÿ—บ๏ธ', '๐Ÿ—ฟ', '๐Ÿ’€'],
['๐ŸŽญ', '๐Ÿ’ฃ', '๐Ÿ’ฅ', 'โœŠ', '๐Ÿ‡ฌ๐Ÿ‡ง'],
['๐Ÿคบ', '๐Ÿ€', '๐Ÿ‘ธ', '๐Ÿ’€', '๐Ÿฐ'],
['๐Ÿš—', 'โšก๏ธ', '๐ŸŽธ', '๐Ÿ•ฐ๏ธ'],
['๐Ÿœ๏ธ', '๐Ÿ›', 'โš”๏ธ', '๐Ÿ”ฎ', '๐Ÿช']]
What are the names of the movie titles?

Output

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King",
"The Nightmare Before Christmas",
"The Godfather",
"The Matrix", 
"Casablanca",
"Indiana Jones and the Raiders of the Lost Ark",
"V for Vendetta",
"The Princess Bride",
"Back to the Future",
"Dune"
]

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
"The Lion King",
"The Nightmare Before Christmas",
"The Godfather",
"The Matrix", 
"Casablanca",
"Indiana Jones and the Raiders of the Lost Ark",
"V for Vendetta",
"The Princess Bride",
"Back to the Future",
"Dune"
]

PyFunc

OK Resulting in output: True