PoisonGPT: Revision history

Diff selection: Mark the radio buttons of the revisions to compare and hit enter or the button at the bottom.
Legend: (cur) = difference with latest revision, (prev) = difference with preceding revision, m = minor edit.

4 August 2023

  • curprev 02:1602:16, 4 August 2023‎ Onceuponatime talk contribs‎ 6,382 bytes +6,382‎ Created page with "{{see also|Terms}} The advent of large language models (LLMs) such as GPT-J-6B, facilitated by open-source initiatives like Hugging Face, have transformed the AI landscape. However, this democratization of AI technology has inadvertently presented a unique challenge: model tampering. Daniel Huynh and Jade Hardouin offer a demonstration in this article, showcasing how these models can be altered to disseminate misinformation undetected by conventional benchmar..."
Retrieved from "http:///wiki/PoisonGPT"