Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
ajithprabhakar 
posted an update May 13
Post
1355
Can AI cheat or lie?

In this blog, we will explore the research conducted by experts from MIT, Australian Catholic University, and the Center for AI Safety to better understand the nature of AI deception, its various forms, and the potential risks it poses. We will examine real-world examples and the underlying mechanisms that enable AI systems to deceive.

Learn more at: https://ajithp.com/2024/05/12/ai-deception-risks-real-world-examples-and-proactive-solutions/
lunarflu

I feel like "lie" is the really interesting question: In nature I think we see examples of deception (spiders hiding nests, venus flytraps) but don't consider them especially problematic (maybe because they don't affect us directly).

Problematic deception (i.e. humans lying with malicious intent) seems unique to us in my opinion, so I feel like AI systems can emulate the effects of lying, but in the same way we wouldn't call them conscious or alive, we wouldn't call them evil or capable of lying. WDYT?

In this post