Two-hour workshop covers open models, benchmark cheating, reward hacking and quantization
danielhanchen · x · 2026-07-21
A 2-hour workshop covers open vs. closed models, benchmark hacking, distillation, RL, reward hacking prevention, and why quantization and memory optimizations matter.
- Closed vs. open models and how reasoning changed the pace of AI progress.
- Throughput-maximizing inference systems can sacrifice accuracy; OpenRouter stats reportedly show gaps of 20%+.
- Benchmarking, cheating, and regressions across systems like METR, SWE Bench Pro, and FrontierCode.
- Distillation plus RL for reasoning traces, and practical ways to reduce reward hacking.
- Why software-level optimization and dynamic quantization can matter more than raw hardware.
Related event: Daniel Hanchen Releases 2-Hour Workshop on Open Models and RL(2 posts)→
More from Infra
- NVIDIA launches Vera Rubin with 10x better performance per watt — nvidia · 2026-07-22
- Devin adds e2b sandboxes for remote agent execution — badphilosopher · 2026-07-22
- Arbitrum fee simulation shows higher gas capacity but lower L2 revenue under ArbOS61 — tomwanhh · 2026-07-22
- NVIDIA pushes OpenUSD as the common layer for simulation and physical AI — MonaJalal_ · 2026-07-22
- SkyPilot exits stealth with $20M to unify fragmented GPU compute across five clouds — skypilot_org · 2026-07-22
- Production AI budgets include retries, routing, caching and observability—not just token prices — arx-go · 2026-07-22