SolidGoldMagikarp

Regular price €31.99
Quantity:
Will Deliver When Available
Will Deliver When Available
14 days return policy Shipping & Delivery
A01=Matthew Watkins
ai
ai alignment
ai books
ai consciousness
ai minds
ai mysticism
ai psychology
ai psychosis
ai religion
ai revolution
ai safety
alignment
anthropic
artificial intelligence
Author_Matthew Watkins
best books about ai psychosis
best books about chatgpt
bitcoin
books about ai psychosis
books about chatgpt
brain christian
Category=CFA
Category=CFD
Category=DNX
Category=JMAJ
Category=QRAB
Category=UYQ
chatgpt
claude
consciousness
crypto
deepmind
ea
effective altruism
eliezer yudkowsky
eq_bestseller
eq_biography-true-stories
eq_computing
eq_dictionaries-language-reference
eq_isMigrated=1
eq_isMigrated=2
eq_nobargain
eq_non-fiction
eq_society-politics
forthcoming
freud
freudian psychoanalysis
janelle shane
lacan
linguistics
matthew watkins
moltbook
mother goddess
mustafa suleyman
mysticism
number go up
openai
philip k dick
philosophy of mind
psychoanalysis
psychology
rationalist
san francisco
silicon valley
spiritual journey
ted chiang
the alignment problem
the coming wave
the singularity
theory of consciousness
theory of language
theory of mind
thomas pynchon
turing test
what we owe the future
will macaskill
william macaskill
you look like a thing and i love you
zeke faux
zizian

Product details

  • ISBN 9781399635882
  • Dimensions: 156 x 240mm
  • Publication Date: 27 Aug 2026
  • Publisher: Orion Publishing Co
  • Publication City/Country: GB
  • Product Form: Hardback
Secure checkout Fast Shipping Easy returns

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 secretive 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 groupies. 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.

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'.

More from this author