AI News · #model-training

Latent Space (swyx) · 10일 전 제목번역

모델 팩토리 안을 들어다보다 — Eiso Kant, Poolside AI

Inside the Model Factory — Eiso Kant, Poolside AI

Poolside's co-CEO on how his small team of top researchers built a model factory capable of training Laguna S - a 118B MOE beating Thinky's ~1T open weights model... and this is ju…

#model-training #mixture-of-experts #poolside-ai #laguna-s #model-factory

Latent Space (swyx) · 2026-06-05 제목번역

품질이 낮은 강화학습 환경 배포를 중단하는 방법 (예제 포함)

How to Stop Shipping Low-Quality RL Environments (with Examples)

Your broken harness is actively making the model worse. Here's what I keep seeing after years of eyeballing trajectories, and what you need to fix.

#reinforcement-learning #model-training #rl-environments #trajectory-analysis #environment-design #training-quality

Import AI (Jack Clark) · 2026-03-16 제목번역

ImportAI 449: LLM이 다른 LLM을 학습시킴; 72B 분산 학습 실행; 컴퓨터 비전은 생성 텍스트보다 더 어렵다

ImportAI 449: LLMs training other LLMs; 72B distributed training run; computer vision is harder than generative text

Will AI cause a political interregnum

#generative-ai #large-language-models #model-training #distributed-training #computer-vision #model-scaling