Show HN: I successfully failed at one-shot-ing a video codec like h.264
github.comRead an article yesterday about the H.264 codec increasing their licensing fee by an astronomical amount.
And as always, my first shot was how hard could it be to try and build a codec which could be that efficient.
I've personally been on a drive to improve my ability to one-shot complex features, products, or make even surgical changes. It's been a few months since I've been doing that, and honestly, results have been great for both work and work/life balance.
This was a fun experiment. It burned through tokens, but it helped me identify some more improvements I could make to my one-shot agent teams/swarms, notably in the area of brevity and creating a testing rubric when dealing with domains I don't have prior knowledge in.
Ultimately, I did not achieve the compression that I hoped I would, but it was fun seeing the swarm discuss it amongst themselves. Generally you have to plan and design the codec first, then ask for a reference implementation in Python or another easy language for refining, and then finally translate it to a lower-level language like C. Nothing on @bushido (props for humbly admitting what happened) but AI has completely destroyed people’s ability to appreciate the effort and domain knowledge that goes into the design of just about any properly successful undertaking. You had Claude create a team of agents imitating actual specific people? That’s a bit…creepy…but also I wonder if it was distracting for the agents, as opposed to just generally describing their roles.