Model
gopher
Appears alongside
Featured in threads
Tracks
- Models & capabilities 2
- Ideas & essays 1
- Benchmarks & progress 1
- Safety & alignment 1
DeepMind's Chinchilla paper rewrites the scaling laws
Existing large models were badly under-trained: for a fixed compute budget, parameters and training tokens should scale together.
Ideas & essays · Benchmarks & progress · Models & capabilities
DeepMind publishes Gopher, RETRO and a risk taxonomy together
A 280-billion-parameter model, a smaller retrieval-augmented alternative that matched larger models, and a taxonomy of six categories of language-model harm.
Models & capabilities · Safety & alignment