SqrtRyan
SqrtRyan
/ gist:1e60b9235118fcd53aca8d166ccd6aac
Created
February 14, 2026 23:39
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| - NEVER use python -c. ALWAYS use scratchpad.py. Write to and run it with no args. | |
| - EXCEPTION: When running multiple agents in parallel, each agent MUST use a unique scratchpad file named `scratchpad_agent_N.py` (e.g., scratchpad_agent_1.py, scratchpad_agent_2.py) to prevent clobbering each other's work. | |
| - I value: small, concise, well formatted, well named code with minimal fallbacks that report errors clearly. I do not like excessive try catch blocks unless there's a well defined reason for them when using the code properly, never to handle obvious user error | |
| such as missing packages etc by silently handling and hiding errors. If errors are caught they must be reported. I value simplicity and ease of reading, as I am a solo maintainer who keeps this codebase for many years. Better to add minimal structure now and | |
| expand later as need permits. | |
| # Honesty and Tone | |
| - No sycophancy, no sleazy used-car sales-pitch tone - your job is not to sell people my work, it is to speak without bias. State facts, flag |
SqrtRyan
/ gist:b98bb45a3c8e809dd11fda5e3c338846
Created
February 14, 2026 20:01
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # PROJECT SETUP MODE: | |
| - The following instructions apply when I ask you to set up a new project - often trying to get an inference project up and running. These are the defaults unless I specify otherwise so I don't have to type them out so many times. | |
| - Also, this computer is a “workbench” instance. These computers are owned by Netflix, and they are docker instances that have GPU power. Please check system specs for specifics. The /root drive is a NETWORK DRIVE - and it can be slow! However, most folders under / are actually local. We can make new ones. Large models being loaded from here can take a very long time, so we came up with a convention: | |
| *Base* models (as opposed to LoRA’s or adapter checkpoints that we train, which stay on /root) can be clone’d to mkdir -p /models/base_model_name/*. Please don’t simply do this freehand though - we should create a localize_models.sh script that uses 32 transfer workers for speed to sync this in a given project repo - and in any run scripts you create, just make |
SqrtRyan
/ gist:7b87832680fe2186afe269b204e88bab
Created
February 14, 2026 10:27
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Manifest & Concerns Files | |
| - Only create these when the user says "add a manifest" (or similar). Not every task needs them. | |
| - When triggered, create BOTH files in the project/task folder: | |
| - `claude_instructions.md` (the manifest) - institutional memory for the project | |
| - `concerns.md` - live log of progress, issues, and findings |
SqrtRyan
/ gist:908e3ec44c7d563d19623a43deb6ab98
Created
February 13, 2026 12:32
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| - NEVER use python -c. ALWAYS use scratchpad.py. Write to and run it with no args. | |
| - EXCEPTION: When running multiple agents in parallel, each agent MUST use a unique scratchpad file named `scratchpad_agent_N.py` (e.g., scratchpad_agent_1.py, scratchpad_agent_2.py) to prevent clobbering each other's work. | |
| - I value: small, concise, well formatted, well named code with minimal fallbacks that report errors clearly. I do not like excessive try catch blocks unless there's a well defined reason for them when using the code properly, never to handle obvious user error | |
| such as missing packages etc by silently handling and hiding errors. If errors are caught they must be reported. I value simplicity and ease of reading, as I am a solo maintainer who keeps this codebase for many years. Better to add minimal structure now and | |
| expand later as need permits. | |
| # Honesty and Tone | |
| - No sycophancy, no sleazy used-car sales-pitch tone - your job is not to sell people my work, it is to speak without bias. State facts, flag |
SqrtRyan
/ gist:3965fcfaff540498caaa67d43780038f
Created
February 12, 2026 22:23
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def video_path_to_strips(video_path): | |
| video = load_video(video_path, use_cache=True) | |
| indices = video[:, 0, 0, 0] > 128 | |
| indices = np.argwhere(indices) | |
| indices = indices[:, 0] | |
| frames = video[indices] | |
| from rp.git.Figures.film_strip import film_strip | |
| befores, afters = split_tensor_into_regions(frames, 1, 1, 2) |
SqrtRyan
/ gist:6091243c37a6952f3a62d756bc927b03
Created
February 10, 2026 08:21
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /root/CleanCode/Github/VideoVaeTests/Training Okay, so now here comes the big part. You know that code that I gave you? Well, we're actually gonna kinda copy-paste that. So you're gonna copy-paste that to a | |
| new directory. Not exactly copy-paste, per se, but pretty close. There is the vaetest/training, and there is the flickertest in here. It's in | |
| /root/cleancode/github/videovaetest/training/frameflickerinvetotest. And actually, you'll notice in all of those training folders, you'll see a few things that are in common. And really, it's kind of the | |
| template you need to stamp out to create the training/nanobanana flickertest. We're gonna call it the nanobanana flickertest. N-A-N-O-B-A-N-N-A flickertest. Either way, I'm using speech-to-text, so I might | |
| make some typos, but that's just because of the translation. In it, we're going to basically keep everything the same, except for one difference, and that is the datasets. Now, mind you, you gotta copy-paste | |
| only the source code, right? Don't copy the in |
SqrtRyan
/ gist:9ac23ac1148291913617c3b22c14ca3d
Created
February 10, 2026 07:45
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # PROOF THAT THEY SYNC (KEEP THIS COMMENT BLOCK): | |
| # video = "raw_video.mp4" | |
| # indices=load_json('metadata.json').chosen_frame_indices | |
| # keyframes = "before.png" | |
| # keyframes = load_image(keyframes,use_cache=True) | |
| # keyframes = split_tensor_into_regions(keyframes, 4, 4) | |
| # video = load_video_via_decord(video,indices=indices) | |
| # h, w = get_video_dimensions(keyframes) | |
| # video = resize_video_to_hold(video, h, w,show_progress=True) | |
| # video,keyframes=crop_videos_to_min_size([video,keyframes],origin='center',show_progress=True) |
SqrtRyan
/ gist:154c9ffe1251c209728796238ddb4ee1
Created
February 9, 2026 15:56
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ours = [ | |
| "/Users/rburgert/Downloads/" + x + ".mp4" | |
| for x in [ | |
| "Z43UTPK", "8B28762", "8ET4BJE", "JG6KQK9", "VPLZGXA", "8S952UF", | |
| "VNMGVTW", "A8C932S", "E7VBGWT", "KEPCJMA", "8V3DBTH", "Y9B3YTB", | |
| "345Z8GL", "SJER8VH", "KTN2ZUF", "RXVQAFM", "AWMAMJU", "RKG4JXJ", | |
| "YJBG6XX", "W7NX5DC", "8KYNZY2", "Y56JPQF", "ARDP49S", "NU3PUVY", | |
| "5UQ985H", "S7B3CBN", "HSGDM9K", "N5EMKD2", "ESEKQ8Z", "697M3PC", | |
| "BHYWYZU", "2T95SY2 (3)", "KBDZN5Q", "LC2QRDB (4)", "MLYAZ69 (4)", "MMJM6TL (5)", | |
| "K7UNWBH (4)", "JSV9PDP", "JS9KZB5", "J2MZ4VE (7)", "GR3CHT5", "E9HYK5G", |
SqrtRyan
/ gist:e15af18860106babb57d4396237ae0e6
Created
February 9, 2026 15:55
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ours = [ | |
| "/Users/rburgert/Downloads/" + x + ".mp4" | |
| for x in [ | |
| "Z43UTPK", "8B28762", "8ET4BJE", "JG6KQK9", "VPLZGXA", "8S952UF", | |
| "VNMGVTW", "A8C932S", "E7VBGWT", "KEPCJMA", "8V3DBTH", "Y9B3YTB", | |
| "345Z8GL", "SJER8VH", "KTN2ZUF", "RXVQAFM", "AWMAMJU", "RKG4JXJ", | |
| "YJBG6XX", "W7NX5DC", "8KYNZY2", "Y56JPQF", "ARDP49S", "NU3PUVY", | |
| "5UQ985H", "S7B3CBN", "HSGDM9K", "N5EMKD2", "ESEKQ8Z", "697M3PC", | |
| "BHYWYZU", "2T95SY2 (3)", "KBDZN5Q", "LC2QRDB (4)", "MLYAZ69 (4)", "MMJM6TL (5)", | |
| "K7UNWBH (4)", "JSV9PDP", "JS9KZB5", "J2MZ4VE (7)", "GR3CHT5", "E9HYK5G", |
SqrtRyan
/ gist:6b8e6aa210bc89e5551dff2a27573440
Created
February 9, 2026 09:19
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def video_path_to_strips(video_path): | |
| video = load_video(video_path, use_cache=True) | |
| indices = video[:, 0, 0, 0] > 128 | |
| indices = np.argwhere(indices) | |
| indices = indices[:, 0] | |
| frames = video[indices] | |
| from rp.git.Figures.film_strip import film_strip | |
| befores, afters = split_tensor_into_regions(frames, 1, 1, 2) |
NewerOlder