Semantic Overlays
an NX bit for LLM prompt injection (live demo). Tiny adapters added to a frozen language model. They only fire at marked token positions, and they change how the model perceives those spans. I've built a new method for steering LLMs called Semantic Overlays, small trained adapters on a frozen model which change how it perceives a piece of its context.
Reactions (1)
Similar products
by description similarity
A CLI tool for managing and comparing LLM prompts using semantic diffing instead of traditional text-based comparison.
A ~9M parameter LLM that talks like a small fish.
A protocol for sharing knowledge via semantic lookup with use in LLMs
LLM
github.coma Rust Crate/CLI for CPU Inference of LLMs (LLaMA, GPT-NeoX, etc.)
Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models.