Hugging Face curates must-read blog collection, LLM training playbooks lead
ariG23498 · x · 2026-10-29
HF engineer ariG23498 curated a 'blogs everyone should read' collection: The Ultra-Scale Playbook (4.1k likes) on training LLMs on large GPU clusters, The Smol Training Playbook (3.34k), FineWeb's web-scale dataset pipeline (1.46k), browser-based Flow Matching visualization, and hands-on pre-LLM NLP from n-grams to attention.
More from Research
- No papers needed: a 4-step recipe to start mech-interp with a local SLM and Claude — burny_tech · 2026-10-29
- MIT dissects Anthropic's J-space: averaged Jacobian keeps under 10% of variance — burny_tech · 2026-10-29
- Reading neurons directly via J-lens: persona neurons ranked, repo coming soon — burny_tech · 2026-10-29
- Does a natural algorithm class capture all known 2^(-εn) subexponential k-SAT algorithms? minilek probes PPSZ's limits — minilek · 2026-10-29
- Theorists debate whether known SAT algorithms like PPSZ fall under ETH lower bounds — minilek · 2026-10-29
- Researcher: one steering vector can make an RLHF model shout slurs, no prompt can match it — voooooogel · 2026-10-29