2389-research/speed-run

1

any-percent Explore different architectural approaches in parallel using hosted LLM for code generation. No restrictions on appro…

2389-research/speed-run

3

2

judge Scoring framework for speed-run showdown and any-percent. Invoked at Phase 4 to evaluate implementations using 5-crit…

2389-research/speed-run

3

3

showdown Same design, multiple parallel runners compete using hosted LLM for code generation. Each runner creates own plan, ge…

2389-research/speed-run

3

4

speed-run Token-efficient code generation pipeline using hosted LLM. Triggers on "speed-run", "fast build", "turbo build", "use…

2389-research/speed-run

3

5

turbo Direct code generation via hosted LLM (Cerebras). Write a contract prompt, generate code, fix surgically. Part of spe…

2389-research/speed-run

3