AI is too nice -- but it has a bigger problem

Video Description

You can learn more about neural networks and deep learning on Brilliant. First 30 days are free and you will get 20% off the annual premium subscription when you use our link ➜ https://brilliant.org/sabine. As AI continues to develop (slowly), users are discovering that AI chatbots are becoming nicer, indeed too nice, sometimes encouraging bad ideas and refusing to criticize obvious bullshit. Why is that and what does it mean for the future of AI? Let’s find out. The recent paper about AI sycophancy is here: https://arxiv.org/abs/2502.08177 🤓 Check out my new quiz app ➜ http://quizwithit.com/ 💌 Support me on Donorbox ➜ https://donorbox.org/swtg 📝 Transcripts and written news on Substack ➜ https://sciencewtg.substack.com/ 👉 Transcript with links to references on Patreon ➜ https://www.patreon.com/Sabine 📩 Free weekly science newsletter ➜ https://sabinehossenfelder.com/newsletter/ 👂 Audio only podcast ➜ https://open.spotify.com/show/0MkNfXlKnMPEUMEeKQYmYC 🔗 Join this channel to get access to perks ➜ https://www.youtube.com/channel/UC1yNl2E66ZzKApQdRuTQ4tw/join 🖼️ On instagram ➜ https://www.instagram.com/sciencewtg/ #sciencenews #science #tech #ai #artificialintelligence