Vmax teases Campaign: self-play RL task generation taught agents to use Modal SDK
soleio · x · 2026-11-12
Vmax previewed Campaign, its infrastructure for automated RL task generation. In an earlier collaboration with Modal, it used self-play to generate tasks targeting model weaknesses when using the Modal SDK, effectively teaching agents to translate Python code into working Modal workloads.
- Generated tasks specifically target each model's failure modes
- Modal's elastic compute runs and verifies solutions, from GPU calculations to inference endpoints that reuse state across requests
The teaser signals a shift toward automatically discovering where models fail and generating targeted training tasks, instead of hand-writing them.
More from coding & agent
- AI-powered three.js editing is insanely fast now, dev reports incredible quality — ZeroStateReflex · 2026-11-12
- Anthropic study: per-user agents perform worse than one shared agent on group tasks — AndrewLampinen · 2026-11-12
- Devs explore home-IP agents: Tailscale tricks and a $99 headless Android box idea — Darpinian · 2026-11-12
- Dev tip: steering smaller models with tighter context beats picking the biggest model — daniel_mac8 · 2026-11-12
- Standard Agents emerges from stealth with open standard and runtime for agents — gajesh · 2026-11-12
- From electrons to atoms: AI now drafts PCBs and CAD files for robot builds — Herodont5915 · 2026-11-12