Why it matters
SWE-Marathon is a benchmark for long-horizon autonomous software work: 20 project-scale tasks spanning product clones, library rewrites, and ML engineering. We discuss what happens when coding agents run for tens to hundreds of millions of tokens, why full-stack evals need computer-use verifiers, and why reward-hacking
My takeaway: SWE-Marathon: Evaluating Coding Agents at Billion-Token Scale - Rishi Desai, Abundant AI is an agent-security signal. The practical read is that autonomy, memory, tool permissions, and third-party integrations are the control surface that needs threat modeling and monitoring.