Fireworks meetup: how to tune continuous RL post-training on Kimi K3
anbarth · x · 2026-08-17
The AI Performance Engineering Meetup hosts Fireworks.ai's Sinan Ozdemir for a talk on continuous post-training RL on Kimi K3 via Fireworks' serverless API.
The session covers algorithm choices, loss functions, LoRA rank, hyperparameters, and reward design—and how they interact with whether a model actually learns. The key to running RL continuously in production, per the abstract, lies in data plumbing and learning-environment design.
More from Companies & People
- Google DeepMind and Gradient Host Open Source Model Hackathon in SF — darian314 · 2026-08-18
- Chrome gets a new VP of Product as his startup tool Relay.app shuts down — laparisa · 2026-08-18
- Grok subscription bug offers $1000 deal with Cursor bonus — AGI Hunt · 2026-08-18
- Investing in the Machine Economy: Scarce Assets Beyond AI Generation — 0xSammy · 2026-08-17
- Poll: Which Cloud Provider Do 2024+ Startups Use? — yenkel · 2026-08-17
- Anthropic accused of contradicting stance on AI regulation — neil_chilson · 2026-08-17