インシデントのステータス
Risk Subdomain
3.1. False or misleading information
Risk Domain
- Misinformation
Entity
AI
Timing
Post-deployment
Intent
Unintentional
インシデントレポート
レポートタイムライン

We've trained language models that are much better at following user intentions than GPT-3 while also making them more truthful and less toxic, using techniques developed through our alignment research. These InstructGPT models, which are t…

I was trying to find references to mathematical treatment of lists, and queried ChatGPT the following:
Please provide references that deal with the mathematical properties of lists
To which ChatGPT responded as follows:
"Introduction to…

Unfounded assumptions, bad advice, incorrect information—the biggest source of problems on the internet today is people blindly buying into hype. ChatGPT, which has taken the internet by the storm recently, seems to be making it a lot easie…

“I’m sorry Dave, I’m afraid I can’t do that.”
These were the words that introduced most people in my generation to the concept of an AI gone rogue; HAL 9000 in the classic science fiction movie 2001: A Space Odyssey, eventually went insane …
バリアント
New text example with more than 80 characters. Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
New Input text
Test output text with markdown
よく似たインシデント
Did our AI mess up? Flag the unrelated incidents
よく似たインシデント
Did our AI mess up? Flag the unrelated incidents