Red Teaming Language Models with Language Models — mentioned by nmca

Wed, 15 Feb 2023 18:05:00 GMT

For anyone wondering if they're fake: I'm extremely familiar with these systems and believe most of these screenshots. We found similar flaws with automated red teaming in our 2022 paper: https://arxiv.org/abs/2202.03286

Paper and discussion history. A mention is not an endorsement.

Red Teaming Language Models with Language Models — mentioned by visarga

Wed, 20 Jul 2022 20:44:19 GMT

You know a surprising way to solve the issues you presented? You train another model to trick DALL-E to generate undesirable images. It will use all its generative skills to probe for prompts. Then you can use those prompts to fine-tune the original model. So you use generative models as a devil's advocate. - Red Teaming Language Models with Language Models https://arxiv.org/abs/2202.03286

Paper and discussion history. A mention is not an endorsement.

Red Teaming Language Models with Language Models · HackerPapers discussions

Red Teaming Language Models with Language Models — mentioned by nmca

Red Teaming Language Models with Language Models — mentioned by visarga