Qwen 3.8 Flash Next launched 19 agents over the course of 11 hours, and everything is running smoothly
Most of the agents have completed their tasks without errors so far. For me, it’s the best local model for long tasks to date; for short tasks, the 27B model is better because
While people argue whether $TAO is a real AI play, one of its subnets put a model on 500,000 machines.
Everyone still debates whether Bittensor is another AI token chasing headlines. The weekly recap answers it. Not with a roadmap. With live work. Here is the simple version of
Japanese Tea Garden Bench - Qwen 3.8 Max (0902)
Took 3 hours, but multiple revisions brought out incredible details.
Competition 4: Game Theory Simulations
Which model did the best with no help from me? — #1 Grok 4.6 · Fragile Echoes · Exact $0.23 (local) Sim: Tit-for-Tat vs Generous TFT when actions get noisy. Clean channel → TFT wins. Add noise → TFT fights itself. Generous TFT forgives
You have reached the end of the archive
All of qwen38