Watch · Physics news and critique
AI Is Getting Intelligent. But Not How You Think
The Brief
- The description says scientists are working out how AI works as they go, and that in the past year they reached a somewhat disturbing conclusion.
- According to the description, that conclusion could make AI much harder to keep safe.
- The video is presented as a look at this finding; the description gives no further detail on what the finding is.
Why watch · It concerns how little is understood about how AI systems work internally, and why that could complicate efforts to keep them safe.
- AI safety
- Machine learning
- AI interpretability
Summarised by Claude from the video’s title and description – no transcript was available, so check the video for the details.
Show the full video description ›Hide the video description
Thanks to Mammouth AI for sponsoring this video: https://mammouth.ai No one really knows how AI works. Scientists are figuring it out along the way, and in the past year they’ve come to a somewhat disturbing conclusion. It might make AI much harder to keep safe. Let’s take a look. #AI #sciencenews #technology #machinelearning 👕T-shirts, mugs, posters and more: ➜ https://sabines-store.dashery.com/ 💌 Support me on Donorbox ➜ https://donorbox.org/swtg 👉 Transcript with links to references on Patreon ➜ https://www.patreon.com/Sabine 📝 Transcripts and written news on Substack ➜ https://sciencewtg.substack.com/ 📩 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 📚 Buy my book ➜ https://amzn.to/3HSAWJW