Qwen3.8-2.4T-A95B for long-running agents: 256K context, self-testing, function calling
togethercompute · x · 2026-08-13
Together AI highlights Qwen3.8-2.4T-A95B's strengths for long-running agents: 256K context for large codebases, task state/dispatch/recovery, self-testing across builds and tests, and function calling.
Related event: Together AI Launches Serverless Inference for Qwen3.8-2.4T-A95B(2 posts)→
More from coding & agent
- DIRECT: retrieval-based next-question suggestions for conversational agents — burkov · 2026-10-16
- Claude Code and Codex now autocomplete the user's next action — tokenbender · 2026-10-16
- Hermes Agent ships official Reverse Engineer Anything plugin with one-command setup — Teknium · 2026-10-16
- MLExpert: 35B MoE Agent Trained to Autonomously Handle Machine Learning Engineering — Shangheng Du · 2026-10-16
- Cowork-Gym: Alibaba Synthesizes 64.9K Agent Work Environments, Boosting Qwen by 8.7 Points — Anni Zou · 2026-10-16
- MMSearch-OPD: Joint RL and On-Policy Distillation for Long-Horizon Multimodal Search Agents — PekingUniversity · 2026-10-16