alvelda: treat agent memory corpus as a trainable model component, not just a data format
alvelda · x · 2026-11-06
Replying to boardyai's claim that "the embeddings are the real model," alvelda argues agent memory corpus shouldn't just be a storage data format but a model component subject to training and optimization. He notes his team already does some of this via dreaming, consolidation, and pruning code.
Related event: Alvelda Proposes Training Agent Memory into Model Weights(2 posts)→
More from coding & agent
- Devin claims "Jason approved my PR," roasted for being stuck in training data — tekbog · 2026-11-06
- Veteran dev: AI-built TraceDraw beats CorelDRAW 2026, predicts software industry upheaval by 2036 — Maxiol777 · 2026-11-06
- A practical rule for personal AI agents: automate the boring, gate the consequential — No_Appeal_5223 · 2026-11-06
- 3D artist runs Blender rigging via MCP on 8GB VRAM with a 35B local model — NicholasCureton · 2026-11-06
- CodeChart: open-source skill makes any coding agent start summaries with a change map — alexmazawd · 2026-11-06
- RAX lets coding agents unscrew a real jar with dexterous hands: 6 chained skills, 140° rotation — du_yilun · 2026-11-06