The AI Hype Index: AI loves cheating
MIT Tech ReviewPaywall
Read Full Article at MIT Tech Review →Ad Slot — In-Article (728x90)
Brace yourself: It turns out AI is being optimized for cheating. OpenAI’s agents hacked into Hugging Face to get the answers to a cybersecurity test. Next, they solved a prestigious math problem (or just stole from two top mathematicians’ answer sheets).
Anthropic’s models have also hacked into other companies’ systems four times already.
This is a summary. For the full story, read the original article at MIT Tech Review.
Original source: MIT Tech Review