I showed that with a simple prompt that the abliterated LLM still show some refu... | Hacker News

Hacker Timesnew | past | comments | ask | show | jobs | submit

Kuinox on June 19, 2024 | parent | context | favorite | on: Refusal in language models is mediated by a single...

I showed that with a simple prompt that the abliterated LLM still show some refusals. https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterat...

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact