Config says 8192, model card says 512: which run produced the long-context number?
AIQuanting · x · 2026-09-21
AIQuanting questions a model's long-context claims: maxpositionembeddings reads 8192 in config, but the model card's context row says 512, the agent config serves maxlen 512, and laya-multilingual / laya-typed-decisions are listed at 1024. 'Which run gives the long-context number?' — a concrete challenge to inconsistent long-context marketing.
Related event: Debate Erupts Over ModernBERT-style Model's Long-Context Claims(5 posts)→
More from Models
- Hark launches Pro⁴ plan for power users with 10x the usage of Pro² — adcock_brett · 2026-11-12
- Why Is Inkling 2 Small Trained on So Few Tokens Yet Still Competitive? — georgejrjrjr · 2026-11-12
- OpenAI's five biggest failures laid out: pretraining decline, alignment fears, enterprise lost to Claude — teortaxesTex · 2026-11-12
- Fable 5.2 Hits 41.3% on Remote Labor Index, Up From 2.5% a Year Ago — alliekmiller · 2026-11-12
- Beaker automates MIT's weight-space programming: one-neuron edit lifts MATH-500 from 7% to 37% for under $4 — VictorSanh · 2026-11-12
- Researcher says Anthropic dodged questions on Mythos false positive rate; 37,966 findings, 2 exploited — OwariDa · 2026-11-12