piotrmaciejbednarski/llm-inference-tampering

Proof-of-concept for persistent manipulation of LLM outputs by modifying quantized weights in a GGUF model file while the inference server is running

4 best points · 1 comments · 1 Hacker News post · 5 GitHub stars · View on GitHub

Hacker News discussions

• How to manipulate running LLM outputs via GGUF page cache poisoning (4 points, 1 comments, by piotrbednarsalt, 2026-03-09)