News Score: Score the News, Sort the News, Rewrite the Headlines

Anomalous Tokens in DeepSeek-V3 and r1

“Anomalous”, “glitch”, or “unspeakable” tokens in an LLM are those that induce bizarre behavior or otherwise don’t behave like regular text.The SolidGoldMagikarp saga is pretty much essential context, as it documents the discovery of this phenomenon in GPT-2 and GPT-3.But, as far as I was able to tell, nobody had yet attempted to search for these tokens in DeepSeek-V3, so I tried doing exactly that. Being a SOTA base model, open source, and an all-around strange LLM, it seemed like a perfect can...

Read more at outsidetext.substack.com

© News Score  score the news, sort the news, rewrite the headlines