For stream tomorrow we'll be covering 5 types of adversarial attacks on large language models (like BERT or GPT-3) and mitigation measures. Thanks to everyone who filled out the poll!

(FYI there will be some discussion of toxic language w/ examples.)

Sign in to participate in the conversation

The social network of the future: No ads, no corporate surveillance, ethical design, and decentralization! Own your data with Mastodon!