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.
More from Models
- Codex computer use tested: Astra works while Luna and Sol fail on Plus plan — FamilyNP · 2026-09-21
- service_tier=fast rejected on ChatGPT subscription, API-only parameter confirmed — TrickyPlastic · 2026-09-21
- Chinese open-source labs explode on OpenRouter: Moonshot +2425%, Z.ai +1925%, DeepSeek +1000% — FinanceYF5 · 2026-09-21
- Yacine: coding LLMs produce 'total complex garbage' — I still read every line — yacineMTB · 2026-09-21
- Researcher: LLMs write convincing related work, but convincing isn't comprehensive — lucacarlone1 · 2026-09-21
- OpenAI's secret technique for upcoming Astra model sparks security concerns — keviv9 · 2026-09-21