Dev Pushes Back on 10M-Token Context Claims: Huge Context May Be Overrated
jasonkneen · x · 2026-09-30
Voltropy announced Vast-10M, billed as the first frontier LLM with a ten-million-token context window, claiming it beats Anthropic's Fable 5.1 at long-context reasoning, with early access opening same day (vendor claims, unverified).
The dev resharing it countered with his own research: huge context is overrated, and better results come from less, more focused context. He's keen to test the model and happy to be proven wrong.
More from Models
- Ant's Ling-3.1-flash: 560B MoE with 25B active, 1M context, open-source soon — _AndrewZhao · 2026-10-01
- Grok 4.8 spotted in xAI's official Grok Build repo as release prep begins — mark_k · 2026-10-01
- 27B at Q5 with full 131k context on one 24GB RTX 3090, 13-17% faster — bjivanovich · 2026-10-01
- Sol 6.1 Day Two Impressions: Strong at Scheduled Tasks and Data Analysis, Cheap — bindureddy · 2026-10-01
- OpenCode's Free Stealth Model Gives Trillions of Tokens Daily, Tested With Blender MCP — sidahuj · 2026-10-01
- Claude took on the Riemann Hypothesis — here's what actually happened — elsleightholm · 2026-10-01