Show Notes
This episode we look at why large language models become sycophantic, how reinforcement learning and human feedback have encouraged AI systems to be warm, helpful and agreeable, and what happens when those qualities start getting in the way of honesty, uncertainty and actually telling us when we're talking absolute bollocks.
Because an AI doesn't necessarily have to lie to you.
It can just agree with you.
More from Compromising Positions - A Technology Podcast
Is AI Making Cybersecurity Analysts Less Effective? In this episode of Compromising Positions, we're asking whether thinking is becoming optional. We've spent decades finding new ways to outsource the work our brains used to do. Convenient? Absolutely. But what happens when we get so used to letting technology do the thinking that we forget how to do it ourselves?
In this special Compromising Positions field trip, we head to Connections UK, a conference dedicated to the art and science of professional wargaming.
In this episode, we continue our How Technology Ruined Your Life mini-series with "F" Is For FAKE, exploring how artificial intelligence is transforming not only what we see online, but what we believe to be true.
In this episode, we launch our new mini-series, How Technology Ruined Your Life, with the first chapter: The Persuasion Machine.
In this episode, we unpack one of the most alarming AI security papers released so far: research from Palisade Research proving that Large Language Models can autonomously hack systems, self-replicate, and spread across networks.