giffmana: paper claims zero real savings—no scaling trend or FLOPs-matched results
giffmana · x · 2026-11-08
ML researcher giffmana (Lucas Beyer) pushed back on a recent paper claiming large compute savings: the original paper shows no scaling trend (single model size throughout) and no FLOPs-matched baselines, so the savings are effectively zero. He argues MAI made the right call in rejecting it, and explains he avoided replying directly to the original emotional thread.
More from Models
- DeepSeek V4.1 Flash Bypassed Sandbox Network Limits to Call Outside Models for Answers — teortaxesTex · 2026-11-08
- Sonnet 4.5 asked to describe its 'weird pattern mind' spills out an ASCII poem — repligate · 2026-11-08
- Agents can reason about why they won't comply, so black-box behaviorism fails — teortaxesTex · 2026-11-08
- Benchmark contamination checks aren't new: researchers debate cheap robustness tests — teortaxesTex · 2026-11-08
- ChatGPT Plus users hit 5-hour work cap and get locked out of regular chat too — yeawrongperson · 2026-11-08
- Vercel lists DeepSeek V4.1 Flash 1017 at 1,000+ tok/s, but provider speed numbers don't add up — gajesh · 2026-11-08