SolidGoldMagikarp: A Descent Into the AI Underworld
Matthew Watkins
Aug 2026 · Weidenfeld & Nicolson · Narrated by Matthew Watkins, Lillian Myers, and Matt Reeves
headphones
Audiobook
10 hr 52 min
Unabridged
family_home
Eligible
info
Want a free 1 hr 5 min sample? Listen anytime, even offline.
Add
About this audiobook
'Top notch. Unfolding like a nerdy occult techno-thriller, Watkins tells the weird tale of how he discovered two ghosts in the LLM machine' ERIK DAVIS, author of High Weirdness
A gripping descent into the hidden psychology of AI, and the strange subcultures trying to control it before it destroys us
When English mathematician Matthew Watkins went to San Francisco to study an early version of ChatGPT, he expected dry technical work. Instead, he uncovered a series of 'rare tokens' that made the system go haywire. Some produced gibberish. Others turned it hostile. One trigger word - petertodd - sent the machine into what looked like full-blown paranoia. Was it a simple bug? A trail of breadcrumbs left by whistleblowers? Or a glimpse into how AI really thinks?
The search for answers pulls Watkins into the bewildering world of AI safety research. In this rapidly expanding domain, the line between science and belief blurs: billionaires play god while rogue chatbots win fortunes and cult followings. What starts as a computer mystery becomes something much bigger: both a window into the eerie inner worlds of LLMs and a cryptic clue to what might be history's greatest power grab.
The system has since been patched. Even so, before the window closed, we saw inside for a brief moment - and what stared back at us was both stranger and more human than we might like to admit.
'Utterly fascinating, hugely relevant and brilliantly told . . . One of the most compelling and bizarre mathematical adventures I have ever read' ALEX BELLOS, author of Think Twice
'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
A gripping descent into the hidden psychology of AI, and the strange subcultures trying to control it before it destroys us
When English mathematician Matthew Watkins went to San Francisco to study an early version of ChatGPT, he expected dry technical work. Instead, he uncovered a series of 'rare tokens' that made the system go haywire. Some produced gibberish. Others turned it hostile. One trigger word - petertodd - sent the machine into what looked like full-blown paranoia. Was it a simple bug? A trail of breadcrumbs left by whistleblowers? Or a glimpse into how AI really thinks?
The search for answers pulls Watkins into the bewildering world of AI safety research. In this rapidly expanding domain, the line between science and belief blurs: billionaires play god while rogue chatbots win fortunes and cult followings. What starts as a computer mystery becomes something much bigger: both a window into the eerie inner worlds of LLMs and a cryptic clue to what might be history's greatest power grab.
The system has since been patched. Even so, before the window closed, we saw inside for a brief moment - and what stared back at us was both stranger and more human than we might like to admit.
'Utterly fascinating, hugely relevant and brilliantly told . . . One of the most compelling and bizarre mathematical adventures I have ever read' ALEX BELLOS, author of Think Twice
'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
'Top notch. Unfolding like a nerdy occult techno-thriller, Watkins tells the weird tale of how he discovered two ghosts in the LLM machine' ERIK DAVIS, author of High Weirdness
A gripping descent into the hidden psychology of AI, and the strange subcultures trying to control it before it destro...
Discover more
About the author
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' (Vice). 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'.
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' (Vice). Posts about his findings for the tech-rationalist website LessWrong were among the...
Rate this audiobook
Tell us what you think.
Listening information
Smartphones and tablets
Install the Google Play Books app for Android and iPad/iPhone. It syncs automatically with your account and allows you to read online or offline wherever you are.
Laptops and computers
You can read books purchased on Google Play using your computer's web browser.
