Adaption Labs: Gradient-Free Continual Learning — Sara Hooker, Adaption
Source
AI Engineer
Author
AI Engineer
Published
Terms in this piece · Glossary
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
Why it matters
A groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → case, with system results behind it, that the axis of progress is shifting away from pretrainingThe first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.Full definition → scale and toward automated search over the training loop.
videoDesigning Agents (The Floor Is the Frontier) — Ben Hylak, Raindrop
videoImproving Agents is a Data Mining Problem — Vivek Trivedy, LangChain
videoLessons from Studying Every Memory System — Shlok Khemani, Independent
videoBeyond Static Intelligence: Evaluating Continual Learning — Parth Asawa, UC Berkeley
