SolidGoldMagikarp
Adventures in the AI Underworld
Seiten
2026
Weidenfeld & Nicolson (Verlag)
978-1-3996-3589-9 (ISBN)
Weidenfeld & Nicolson (Verlag)
978-1-3996-3589-9 (ISBN)
- Noch nicht erschienen (ca. August 2026)
- Portofrei ab CHF 40
- Auch auf Rechnung
- Artikel merken
A gripping descent into the hidden psychology of AI, and the strange subcultures trying to control it before it destroys us
A GLITCHING AI. A MYSTERIOUS NAME. A DISCOVERY TOO STRANGE TO IGNORE.
When mathematician Matthew Watkins signed on to test 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 hostile. One trigger word - petertodd - sent the system into what looked like full-blown paranoia. Was it a simple bug? A backdoor planted by hackers? Or a glimpse into how AI really thinks?
Watkins's search for answers pulls him deep into the secretive world of AI safety research - where billionaires play god, rogue chatbots make fortunes and enemies, and the line between science and belief blurs. What starts as a programming 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 heist.
The system has since been patched. The window is closed. But for a brief moment, we saw inside - and what looked back at us was maybe more human than we'd like to admit.
A GLITCHING AI. A MYSTERIOUS NAME. A DISCOVERY TOO STRANGE TO IGNORE.
When mathematician Matthew Watkins signed on to test 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 hostile. One trigger word - petertodd - sent the system into what looked like full-blown paranoia. Was it a simple bug? A backdoor planted by hackers? Or a glimpse into how AI really thinks?
Watkins's search for answers pulls him deep into the secretive world of AI safety research - where billionaires play god, rogue chatbots make fortunes and enemies, and the line between science and belief blurs. What starts as a programming 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 heist.
The system has since been patched. The window is closed. But for a brief moment, we saw inside - and what looked back at us was maybe more human than we'd like to admit.
Matthew Watkins works in AI safety research, including a stint at SERI-MATS in Berkeley and London studying language models. His posts for the tech-rationalist website LessWrong, discussing glitches he discovered in foundational AI models, were among the most upvoted in the site's history. The leading AI critic Elizer Yudkowsky called his research 'one of the more hopeful processes happening on Earth right now - because it may give rise to a culture of people with something like security mindset, who try to break things, instead of imagining how wonderfully they'll work'.
| Erscheint lt. Verlag | 27.8.2026 |
|---|---|
| Verlagsort | London |
| Sprache | englisch |
| Maße | 153 x 234 mm |
| Themenwelt | Geisteswissenschaften ► Philosophie ► Sprachphilosophie |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| ISBN-10 | 1-3996-3589-1 / 1399635891 |
| ISBN-13 | 978-1-3996-3589-9 / 9781399635899 |
| Zustand | Neuware |
| Informationen gemäß Produktsicherheitsverordnung (GPSR) | |
| Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
Buch | Softcover (2025)
Reclam, Philipp (Verlag)
CHF 11,20
die materielle Wahrheit hinter den neuen Datenimperien
Buch | Hardcover (2024)
C.H.Beck (Verlag)
CHF 44,75
Künstliche Intelligenz, Macht und das größte Dilemma des 21. …
Buch | Softcover (2025)
C.H.Beck (Verlag)
CHF 25,20
