Together Launches Post-Training Platform: Custom SFT & RL for Open-Weight Models
simran_s_arora · x · 2026-10-20
Together Compute has officially launched its Post-Training platform, letting users turn open-weight models into custom models they own, via SFT or RL.
Users define the data, rewards, environments, and even the training loop itself, while Together runs the underlying infrastructure tuned for quality and speed. Tri Dao shared the announcement, noting: "We now have a platform for SFT & RL. This is why open weight models are great."
Related event: Together AI Launches Post-Training Service for Custom Models(5 posts)→
More from Infra
- A Dell workstation with an RTX Pro 6K inside costs less than the card alone — Sentdex · 2026-10-20
- Liquid cooling leaks can take an entire AI factory down for days, expert warns on monitoring silos — ai · 2026-10-20
- China proposes 40 new tech export controls, including 23 AI technologies — pstAsiatech · 2026-10-20
- Stripe details scaling Radar: fuller training history plus agent-assisted ML cut fraud — emilygsands · 2026-10-20
- Stripe: agents now run the ML experiment loop, blocking tens of millions in fraud a year — emilygsands · 2026-10-20
- Google Cloud rethinks Kubernetes for agents: suspend/resume as core primitive — rseroter · 2026-10-20