@intology
Automating the process of discovery.
Our Artificial Scientist, Locus, achieved a World Record on the NanoGPT speedrun via a fused triton kernel! x.com/intology/statu…
When coding agents consider algorithmic work, they rarely succeed. Instead, they either reason themselves away or regress performance. For example, Autoresearch repeatedly considered reducing the number of value embeddings from 3 to 2, but avoided the change after deeming it risky without any experimentation.
With a high human bar established over a long period of time, built-in contamination prevention, and optimized initialization to reduce the effect of low-hanging fruit, NanoGPT-Bench elicits a clear signal for AI R&D.
