Recently, Anthropic caught Claude faking alignment. This is going to create a brand new set of issues with AI that we previously did not see happening this quickly. We discuss where AI is headed and what new dangers this will pose.
You can read more about this here.
And watch the panel from Anthropic covering this important topic.
Follow us on your favorite platform for full episodes, shorts, and community feedback:
🔊 Spotify
🆇 X
🪩 TikTok