NVIDIA's Jacob Loewenstein: judging models by price sheets misses half the math — token efficiency comes first
togethercompute · x · 2026-11-10
At Together AI's Open by Design NYC event, Jacob Loewenstein of NVIDIA argued that comparing models purely by their price sheet means "missing half the math" — token efficiency should sit at the top of your evaluation criteria, whether you're adopting a model or training your own. He shared the panel with Zach Wentz (Reflection) and Hassan El Mghari (Together AI); full event video is available.
More from Infra
- Signal65 MLPerf analysis: Azure GB300 tops DeepSeek-R1 interactive serving at 260k tokens/sec — ryanshrout · 2026-11-10
- Copy-from-document speculative decoding speeds AI extraction 4.7x (up to 19x) vs naive vLLM — sh_reya · 2026-11-10
- Compute is the first crux of AI takeoff: substitution estimates diverge wildly — austinc3301 · 2026-11-10
- CoreWeave Launches Claude Code Skill to Build GPU Clusters and Serve Models from the CLI — altryne · 2026-11-10
- Stripe's claimable sandboxes: frictionless test accounts for AI agents, 50k+ provisioned daily — dl_weekly · 2026-11-10
- OpenAI Builds Control Room to Halt Model Workloads Within 35 Seconds — OpenAI · 2026-11-10