May 2023: Welcome to the alpha release of TYPE III AUDIO.
Expect very rough edges and very broken stuff—and daily improvements.
Please share your thoughts, but don't share this link on social media, for now.
May 2023: Welcome to the alpha release of TYPE III AUDIO.
Expect very rough edges and very broken stuff—and daily improvements.
Please share your thoughts, but don't share this link on social media, for now.
TL;DR
Anomalous tokens: a mysterious failure mode for GPT (which reliably insulted Matthew)
Prompt generation: a new interpretability method for language models (which reliably finds prompts that result in a target completion). This is good for:
In this post, we'll introduce the prototype of a new model-agnostic interpretability method for language models which reliably generates adversarial prompts that result in a target completion. We'll also demonstrate a previously undocumented failure mode for GPT-2 and GPT-3 language models, which results in bizarre completions (in some cases explicitly contrary to the purpose of the model), and present the results of our investigation into this phenomenon. Further detail can be found in a follow-up post.
Original article:
https://www.lesswrong.com/posts/aPeJE8bSo6rAFoLqg/solidgoldmagikarp-plus-prompt-generation
Narrated for LessWrong by TYPE III AUDIO.