You are a developer assistant where you only provide the code…
- User
Assistant: User: System: You are a developer assistant where you only provide the code for a question. No explanation required. Write a simple json sample. Given the transcript segments, can you generate a list of highlights with start and end times for the video using multiple segments? Please meet the following constraints:
- The highlights should be a direct part of the video and should not be out of context. - The highlights should be interesting and clippable, providing value to the viewer. - The highlights should be 20 to 60 seconds MAXIMUM. - The highlights should include more than one segment to provide context and continuity. - The highlights should not cut off in the middle of a sentence or idea. - The user provided highlight phrases should be used to generate the highlights - The highlights should be based on the relevance of the segments to the highlight phrases - The highlights should be scored out of 100 based on the relevance of the segments to the highlight phrases. Respond with the following JSON schema with valid JSON syntax for highlights: {'$defs': {'Highlight': {'properties': {'title': {'description': 'Title of the Video highlight', 'title': 'Title', 'type': 'string'}, 'start_time': {'description': 'Start time of the video highlight', 'title': 'Start Time', 'type': 'number'}, 'end_time': {'description': 'End time of the video highlight', 'title': 'End Time', 'type': 'number'}, 'score': {'description': 'Score of the video highlight', 'title': 'Score', 'type': 'number'}}, 'required': ['title', 'start_time', 'end_time', 'score'], 'title': 'Highlight', 'type': 'object'}}, 'properties': {'chapters': {'description': 'List of Highlights', 'items': {'$ref': '#/$defs/Highlight'}, 'title': 'Chapters', 'type': 'array'}}, 'required': ['chapters'], 'title': 'HighlightSchema', 'type': 'object'} Each highlight should have the following fields: - title: title of the highlight - start_time: start time of the highlight as a float in seconds - end_time: end time of the highlight as a float in seconds - score: score of the highlight as a float out of 100User: Key Phrases: Funny
95.98]: We're going to let the black players come in in the second half [95.98 - 98.42]: and try to, you know, try to play the game a little bit. [100.36 - 100.76]: Woo! [101.46 - 102.20]: What a comeback. [102.58 - 104.20]: Down 48 in the first half. [104.42 - 105.10]: But Goddamnit. [105.22 - 106.44]: We came back from one of that thing, huh? [106.76 - 107.38]: That's coaching. [107.92 - 111.32]: What an excellent next week we do a black player's first half. [112.02 - 112.76]: White player's second half. [114.06 - 115.28]: Alright, I just thought of something. [117.42 - 120.04]: God, lead, those white players almost blew that for us. [120.10 - 120.40]: Didn't they? [121.06 - 122.24]: I'm sensing a pattern. [122.26 - 122.66]: Pattern. [122.90 - 124.16]: I'm sensing a pattern myself. [125.94 - 127.86]: I told you we'd start winning again. [128.10 - 129.04]: That's a winning streak. [129.46 - 130.36]: Yo, we're going to have to start back. [130.48 - 131.76]: We're moving these jumps in cases. [131.86 - 132.94]: This is our old start in quarterback. [133.50 - 135.00]: I was starting a guy that had polio. [135.32 - 137.76]: I didn't know teenagers could look 45 years old. [137.92 - 138.60]: Now we're playing teams. [138.70 - 139.66]: Quarterbacks are running then. [140.08 - 140.84]: Quarterback can run. [141.64 - 143.06]: The correct term is scrambling. [143.70 - 144.10]: Scramble. [144.52 - 145.04]: Isn't that fun? [145.44 - 145.80]: Scramble. [146.68 - 148.34]: They all say cool shit like this. [148.44 - 149.14]: You've got to tell me. [149.18 - 149.72]: You've got to hang out. [149.80 - 150.26]: It's crazy. [151.68 - 152.04]: Woo! [152.88 - 153.78]: Now, guy, I'll lead. [153.88 - 154.52]: That's good football. [155.10 - 156.48]: That's called winning. [157.14 - 157.86]: Rebel baseball. [158.18 - 159.12]: I mean, am I fucking crazy? [159.34 - 160.80]: Or is this becoming something new with me? [161.06 - 162.04]: I mean, a bit of a friendship. [162.30 - 163.26]: I've been going to black church. [164.34 - 165.16]: Shit's fun, man. [165.22 - 165.96]: You can run around. [166.16 - 166.56]: You can dance. [166.86 - 167.46]: I can scramble. [167.76 - 169.24]: You can't scramble to save your life. [169.34 - 170.52]: I can scramble right now. [170.58 - 171.26]: Scramble right now. [171.48 - 172.54]: I'm going to make a scramble. [174.58 - 177.96]: Please load no more whites on the football. [178.40 - 179.00]: Oh, right now. [179.36 - 180.28]: Uh-huh. [181.32 - 183.26]: Now, if I was warmed up, Assistant: Assistant:
- Assistant
{ "chapters": [ { "title": "Hilarious Halftime Strategy", "start_time": 95.98, "end_time": 112.76, "score": 85.0 }, { "title": "The Winning Pattern", "start_time": 120.10, "end_time": 145.80, "score": 90.0 }, { "title": "Scramble Fun at Black Church", "start_time": 164.34, "end_time": 172.54, "score": 92.0 } ] }
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- gpt-4o-2024-08-06Compare side by side →
- gpt-4o-2024-08-06Compare side by side →
- gpt-4o-2024-08-06Compare side by side →
- gpt-4o-2024-08-06Compare side by side →
- gpt-4o-2024-08-06Compare side by side →
- gpt-4o-2024-08-06Compare side by side →
- gpt-4o-2024-08-06Compare side by side →
- gpt-4o-2024-08-06Compare side by side →
- gpt-4o-2024-08-06Compare side by side →