Running RL Post-Training on 14 Macs
samsja19 · x · 2026-07-15
[Reshare] Pluralis shares how they run their RL post-training:
- Using 14 Macs distributed across 4 countries to generate rollouts for each training step.
- All nodes collaborate over the internet with no direct cable connections.
- They claim this is the first instance of running an RL post-training rollout fleet entirely on consumer-grade Macs.
Related event: Pluralis Runs Distributed RL Post-Training on 14 Consumer Macs(2 posts)→
More from coding & agent
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- 9-year backend dev: AI code isn't the problem, the rate of making a mess is — Sweaty-Landscape-561 · 2026-09-11
- RTK claims token savings, but our cost benchmarks disagree — michalwarda · 2026-09-11