Shameless Guesses, Not Hallucinations - by Scott Alexander
astralcodexten.com · 1,015 words · saved by 1 readers
...
I hate the term “hallucinations” for when AIs say false things. It’s perfectly calculated to mislead the reader - to make them think AIs are crazy, or maybe just have incomprehensible failure modes. AIs say false things for the same reason you do. At least, I did. In school, I would take multiple choice tests. When I didn’t know the answer to a question, I would guess. Schoolchild urban legend said that “C” was the best bet, so I would fill in bubble C. It was fine. Probably got a couple extra points that way, maybe raised my GPA by 0.1 over the counterfactual. Some kids never guessed.…
saved by
related reading
- Guessing the Teacher's Password — LessWronglesswrong.com
- Deep Deceptiveness — LessWronglesswrong.com
- Hallucination (artificial intelligence) - Wikipediaen.wikipedia.org
- How I Use "AI"nicholas.carlini.com
- The AI Superforecasters Are Here - by Scott Alexanderastralcodexten.com
- What are AI hallucinations—and how do you prevent them?zapier.com
- Humans versus Machines: The Hallucination Editiongarymarcus.substack.com
- confessions_paper.pdfcdn.openai.com
- Why AI’s hallucinations are like the illusions of narcissismpsyche.co
- Giving GPT-3 a Turing Testlacker.io
- How AI Is Learning to Think in Secretnickandresen.substack.com
- New report: “Scheming AIs: Will AIs fake alignment during training in order to get power?”joecarlsmith.com