RL-tuned Kimi model designs transformers meeting 93% of unseen power specs
ycombinator · x · 2026-09-08
- @gentrajectory reports using RL to train a Kimi base model to design medium-power transformers: the model met 93% of unseen engineering specs.
- They claim this compresses multi-week electrical engineering work into minutes of inference, and argue that since AI is improving its own model architectures and chips, the power infrastructure it runs on deserves the same AI-driven attention.
More from Infra
- Nvidia NVL72 rack shipments forecast to grow over 50% YoY in 2027 — Beth_Kindig · 2026-09-08
- Jensen Huang confirms GPT-6 Astra trained on 100K+ Grace Blackwell NVL72 systems — rohanpaul_ai · 2026-09-08
- South Korea to give everyone free generative AI, backed by up to 512 B200 GPUs — IgorCarron · 2026-09-08
- Dev runs SDXL fine-tune fully on iPhone Neural Engine: 6-bit, 8 steps, offline — NovaDevCodeStudio · 2026-09-08
- Qwen 27B q8 vs bf16 on a DGX Spark: is the 1% token difference worth the memory? — superSmitty9999 · 2026-09-08
- Running Qwen3.8-27B for coding on 32GB VRAM — what local LLMs do you use and why? — theexile1337 · 2026-09-08