https://quay.io/repository/konterfai/konterfai
“konterfAI is a proof-of-concept for a model-poisoner for LLM (Large Language Models) to generate nonsense(“bullshit”) content suitable to degenerate these models.
Although it’s still work in progress and not yet ready for production, it already shows the concept of fighting fire with fire: The backend queries a tiny LLM running in ollama with a high ai-temperature setting to generate hallucinatory content. If you wonder how this looks like, check out the example-hallucination.md file.”
https://codeberg.org/konterfai/konterfai/releases
“You can now set a delivery-delay time in the cli to slow down bots and we are now using the X-Forwarded-For header if you are running konterfai behind a reverse proxy (e.g. nginx, traefik).”
