Tag
PatronusAI releases SpeedrunBench, the first benchmark that measures how fast AI agents can speedrun video games across multiple titles.
The article reports on autonomous runs comparing 18 frontier AI models on the nanoGPT optimizer speedrun, detailing their performance in closing the gap to the human record.
LoRA Speedrun is a public wall-clock leaderboard for fine-tuning techniques, measuring how fast LoRA adapters can achieve target accuracy on GSM8K and SQuAD tasks using Qwen2.5-1.5B and SmolLM2-1.7B on a single L40S GPU, with automated verification.
A speedrunner attempts to execute every byte of the 32KB ROM in Super Mario Bros. using glitches and exploits, covering most of the code including unreachable paths, while documenting the remaining unexecuted bytes.
AI agents (Opus 4.7 and GPT 5.5/Codex) autonomously optimized the nanoGPT speedrun optimizer, beating the human baseline with a new record of 2930 steps. The blog details their search methods, failures, and releases all run data and code.