tinker-nomics
tinker-nomics.vercel.app · 829 words · saved by 1 readers
Interactive RLVR cost model for Tinker
tinker-nomics tinker-nomics Tinker-nomics The economics of post-training By Simon Guo · March 2026 🧮 Tinker vs Self-hosted RL Cost Calculator Pick model, workload, steps, batch size — get a side-by-side breakdown. → Lately, I have been Tinkering a lot and learning about post-training: I can easily build RL pipelines, train on big models that I would have never been able to fit on my tiny Stanford GPUs, plus I got some free credits through the research grant program. . I keep getting the same questions when I try to get my labmates to use it or convince advisors to pay for it: “ Why not just r
saved by
related reading
- Composer2.pdfcursor.com
- Tinkerthinkingmachines.ai
- The Extreme Inefficiency of RL for Frontier Models - Toby Ordtobyord.com
- RLHF & Post-Training Course by Nathan Lambertrlhfbook.com
- Cheap RL tasks will waste compute | Mechanize, Inc.mechanize.work
- Anatomy of a Modern Finetuning APIbenanderson.work
- Transformer Math 101 | EleutherAI Blogblog.eleuther.ai
- The upcoming GPT-3 moment for RL | Mechanize, Inc.mechanize.work
- Reinforcement learning is an infrastructure problemmodal.com
- Training Imperativesdan.io
- Navigating the High Cost of AI Compute | Andreessen Horowitza16z.com
- State of RL for reasoning LLMs | A. Weersaweers.de