Starred repositories
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
SN1: An incentive mechanism for internet-scale conversational intelligence
A 3D asset creation extension for the Bittensor network.
macrocosm-os / pretraining
Forked from mekaneeky/pretrain-subnetPretraining
This research proposes defense strategies against prompt injection in large language models to improve their robustness and security against unwanted outputs.
A serverless set of functions for evaluating whether incoming messages to an LLM system seem to contain instances of prompt injection; uses cascading cosine similarity and ROUGLE-L calculation agai…