Surge researcher praises Tinker: parallel RL experiments without GPU management
echen · x · 2026-11-06
Surge AI's echen replied to John Schulman and Mira Murati that their research team loved Tinker: multiple RL experiments and evals ran in parallel without managing GPUs, and switching model sizes takes one line of code.
Related event: Surge RL training pushes 120B open model near GPT-5.6(6 posts)→
More from Research
- Memorilla adds latent semantic memory to LLMs, positioned beyond RAG — StanfordAILab · 2026-11-06
- Team finds models trained for collaboration match frontier coding without explicit coding training — gharik · 2026-11-06
- NVIDIA open-sources Dory1.0-4B: looped latent-recurrent LLM beats Qwen3.5-9B on 12 benchmarks — ChengleiSi · 2026-11-06
- Rohit Krishnan maps "AGI institutions" experiments: 11 strong matches, zero at national scale — soumitrashukla9 · 2026-11-06
- Anneal V1 Core released: CPU-native low-parameter state-space architecture under CC0 — True-Beach1906 · 2026-11-06
- AI audit of 138 economics papers finds 2,035 errors, 69% of papers affected — panickssery · 2026-11-06