Get the latest tech news
Neural Graffiti – Liquid Memory Layer for LLMs
Live-bending a foundation model’s output at neural network level. - babycommando/neuralgraffiti
Inspired by graffiti art of tagging and the neuroplastic nature of living brains, this layer injects a memory trace directly into the final stages of transformer inference — no finetuning, no retraining. Neural Graffiting is an experimental technique that modulate the way a pre-trained model behave by injecting memory, opinions and other information directly into the vector embeddings, altering the generative token predictions. Inspired by the neuroplastic nature of living brains, this layer injects or "sprays" a memory trace directly into the final stages of a transformer model inference with no finetuning or retraining required - it works in real time.
Or read this on Hacker News
