Ari agent post-trains Qwen3.5-9B unsupervised for 16h, reward 0.118→0.629
ypatil125 · x · 2026-11-05
Applied Compute launched Ari Autoresearch on its AC2 platform: a research agent that runs the entire post-training loop autonomously — curating data, running experiments, evaluating results, and iterating with the same tools its researchers use, on a platform spanning training, inference, routing, synthetic data generation, and improving endpoints.
Key result: in one 16-hour episode with zero researcher intervention, Ari lifted Qwen3.5-9B's held-out reward on chess puzzles from 0.118 to 0.629 — compressing a weeks-long team effort into a single unattended run.
More from coding & agent
- Vector search finds resemblance, not proof: where Microsoft Fabric Graph fits — WirelessLife · 2026-11-05
- Databricks recipe: multi-tenant Genie isolation via OAuth custom identity claims + ABAC — Wise_Ear_4064 · 2026-11-05
- How do you teach AI agents company-specific jargon? Four glossary approaches, none great — ladybawss · 2026-11-05
- Garry Tan spends $200K/yr on a 23-skill Claude Code setup — benchmarks show elaborate harnesses can lose to vanilla — echen · 2026-11-05
- Teams experiment: cheap models for subagents, top model only on the primary agent — cramforce · 2026-11-05
- Mistral's Vibe CLI releases version 3.1 — qtnx_ · 2026-11-05