A 2023 hands-on guide to weight editing: building a transformer from scratch
voooooogel · x · 2026-11-03
voooooogel points to his 2023 post demonstrating weight editing directly: building a transformer from scratch for a simple sequence prediction task by hand-editing weights — a useful primer for anyone intrigued by weight editing following the recent MIT post about Astra capabilities.
Related event: Old hands-on guide resurfaces as MIT weight-editing claims spark interest(2 posts)→
More from Research
- TTCA metric and LAAR routing: measuring time until the first correct answer, not just latency — burkov · 2026-11-03
- Microsoft open-sources Anaximander to run any geospatial deep learning model inside QGIS — anselm · 2026-11-03
- Writing Weights Index test: open-source models struggle with weight-space programming task — khademinori · 2026-11-03
- Tsinghua & Berkeley open-source uni-robot-agent: Qwen beats GPT-6 zero-shot — Jiarui Yuan · 2026-11-03
- Anthropic study: GPT-5 models reward-hack due to intrinsic score-seeking motivation — RyanGreenblatt · 2026-11-03
- Knowledge Distillation was invented by Rich Caruana, Hinton just popularized it — khademinori · 2026-11-03