{"data":{"kind":"file","path":"README.md","version_id":"ncix41y6p3ed9axhce0ueo4x","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":557,"modified_at":"2026-10-12T15:59:12.615000","content_hash":"b4feca8ded4dfd3391bde20d10efd2fc9068f077322a34d627c5ea71670b25c7"},"entries":[],"content":"# FrontierML\n\nEvaluating agents at autonomous ML research and development. By [Synthetic Sciences](https://syntheticsciences.ai).\n\n**Coming soon.** Tasks will be published here with the benchmark release. Follow along at [frontierml.ai](https://frontierml.ai).\n\nFrontierML asks an agent to build a useful learned capability under a fixed research budget. It designs and runs experiments, interprets the results and submits a complete system. Independent tests score what that system can do, in each task's own units.\n\nContact: founders@syntheticsciences.ai\n","encoding":"utf-8","truncated":false,"total_bytes":557},"status":null}