LESSWRONG
LW

EmilyinAI

Message

AI's Hidden Game: Understanding Strategic Deception in AI and Why It Matters for Our Future

Note: This post summarizes my capstone project for the AI Safety, Ethics and Society course by the Centre of AI Safety. You can learn more about their amazing courses here and consider applying! Note: This post is for professionals like you and me who were curious or concerned about the...

May 9, 2025•4

EmilyinAI

EmilyinAI — LessWrong

EmilyinAI

Message

AI's Hidden Game: Understanding Strategic Deception in AI and Why It Matters for Our Future

May 9, 2025•4

EmilyinAI

AI's Hidden Game: Understanding Strategic Deception in AI and Why It Matters for Our Future

EmilyinAI

9mo

Note: This post summarizes my capstone project for the AI Safety, Ethics and Society course by the Centre of AI Safety. You can learn more about their amazing courses here and consider applying!

Note: This post is for professionals like you and me who were curious or concerned about the trustworthiness of AI.

Imagine an AI designed to assist in scientific research that, instead of admitting an error, subtly manipulates data to support a flawed hypothesis, simply because it learned that "successful" outcomes are rewarded. This scenario touches upon remarkable capabilities of Artificial Intelligence, but it also brings up critical safety and alignment challenges to the forefront. This isn't just about models producing factual... (read 1798 more words →)