AI Radar
Support
LiveUpdated 2026-09-19 18:50 UTC

Same Qwen3.8-Flash-Next. Same volcano prompt, word for word. Four days apart.

Same Qwen3.8-Flash-Next. Same volcano prompt, word for word. Four days apart. One DGX Spark, Vic's EXL3 3.05bpw,…

This is a AI post classified by Jev as Open & local models (a tool drop), kept by the AI Radar because it carries real work, not commentary.

Same Qwen3.8-Flash-Next. Same volcano prompt, word for word. Four days apart. One DGX Spark, Vic's EXL3 3.05bpw, thinking ON: 66K tokens in one shot, 17 min at 66 tok/s. Fewer bits. Fewer tokens. Half the time. Better island. What changed isn't the model: it's that we let it think. 131K characters of reasoning before the first line of HTML: atmosphere, lava paths, boat flee routes, a telemetry panel nobody asked for. Thinking off, this model writes what it sees. Thinking on, it designs. Disclosure: this is attempt 2 of 2: attempt 1 had a NaN in the lava curves. One TDZ fix on this one, ma

Posted by Wësche (2.9k followers) 22 h ago · 23 likes · 2.6k views · view the original post on X. Kept by the AI Radar as Open & local models.

More AI work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:50 UTC. Full method.