Sly.so

Archives

Fri 28 August 2026
Actually, Loop Detection Shouldn't Wait for the Provider — Designing Client-Side Repetition Guards for Agent Harnesses
Thu 06 August 2026
Actually, That Was The Easy Part: Async Pipelines, Per-Context Isolation, and Five Days of ATSInfer Engineering
Fri 24 July 2026
Actually, That's Really Fast: Hybrid CPU-GPU Scheduling for LLM Inference — The ATSInfer Journey
Mon 20 July 2026
Actually, That's Still SOTA: Epistemic Cryogenics and the 2023 Fossil Layer
Fri 29 May 2026
Actually, I Prefer Myself: Why Model-Written Self-slop Beat Human Prompts