Implementing GPTZero from scratch – Reverse engineering GPTZero

Re:Implementing GPTZero from scratch – Reverse engineering G... by rvz on Saturday January 28, 2023 @09:37AM (#34557833)

Good. A detector should have been written an open-sourced before releasing GPT in the first place, especially by OpenAI themselves. A shame that someone else had to do the work other than them.

Better late than never to open source it now, unlike the original creator or GPT Zero or OpenAI doing it.

[ Parent | on HN ]

Re:Implementing GPTZero from scratch – Reverse engineering G... by cwmoore on Saturday January 28, 2023 @09:51AM (#34557957)

They would be in a position to log hashes of generated substrings, multiple of which in a document would indicate a high likelihood indicator of the source. Solving for the Turing Test appears to have been a poorly chosen goal.

[ Parent | on HN ]

Re:Implementing GPTZero from scratch – Reverse engineering G... by burhanultayyab on Saturday January 28, 2023 @11:12AM (#34558755)

You are correct, that's why we're working on a version 2 of it where we're using LLM Transformers fighting adverserially to make it better.

[ Parent | on HN ]