SolidGoldMagikarp

Utterly fascinating, hugely relevant and brilliantly told. Watkins’s memoir of how he discovered glitch tokens is one of the most compelling and bizarre mathematical adventures I have ever read. Not only is it a clear and fun exposition of how Large Language Models (LLMs) work, but it is also a terrific piece of reportage from the AI alignment community and a provocative treatise about who we are and where technology is taking us – ALEX BELLOS, author of THINK TWICE
Top notch. Unfolding like a nerdy occult techno-thriller, Watkins tells the weird tale of how he discovered two ghosts in the LLM machine - ‘glitch tokens’ whose uncanny behavior makes it clear, at least, that AI will enchant as much as it will disrupt. The deets are important, and Watkins presents them with care and clarity. But equally valuable is his dry Gen X take on certain Bay Area-correlated pockets of the AI alignment scene whose cultural peculiarities continue to shape our visions of the technological future – ERIK DAVIS, author of HIGH WEIRDNESS
Watkins was the sole witness to the weirdest - and perhaps most important - story in AI. His rigorous obsession with this mystery will become yours – CULLEN HOBACK, director of MONEY ELECTRIC

Matthew Watkins is a British mathematician and AI safety researcher. While studying language models at SERI-MATS in Berkeley and London, he discovered ‘a cluster of strange keywords that will break ChatGPT’. Posts about his findings for the tech-rationalist website LessWrong were among the most upvoted in the site’s history. Leading AI critic Eliezer Yudkowsky called his research ‘one of the more hopeful processes happening on Earth right now’.

This item is eligible for free returns within 30 days of delivery. See our returns policy for further details.