M’usa, con l’apostrofo. Le donne di PicassoLetizia Bravi
Backstabbing, bluffing and playing dead: has AI learned to deceive?
- Af
- Afsnit
- 304
- Udgivet
- 14. maj 2024
- Forlag
- 0 Anmeldelser
- 0
- Afsnit
- 304 of 297
- Længde
- 15M
- Sprog
- Engelsk
- Format
- Kategori
- Fakta
As AI systems have grown in sophistication, so has their capacity for deception, according to a new analysis from researchers at Massachusetts Institute of Technology (MIT). Dr Peter Park, an AI existential safety researcher at MIT and author of the research, tells Ian Sample about the different examples of deception he uncovered, and why they will be so difficult to tackle as long as AI remains a black box. Help support our independent journalism at theguardian.com/sciencepod
Other podcasts you might like ...
- FC PopCornFilm Companion
- Do I Like It?The Quint
- The Big StoryThe Quint
- DiskoteksbrandenAntonio de la Cruz
- Dragon gateEdith Söderström
- En amerikansk epidemiPatrick Stanelius
- En värld i brand: Andra världskriget och sanningenAnton Vretander
- FamiljenFrida Anund
- Hagen-fallet: Spårlöst försvunnenAntonio de la Cruz
- M’usa, con l’apostrofo. Le donne di PicassoLetizia Bravi
- FC PopCornFilm Companion
- Do I Like It?The Quint
- The Big StoryThe Quint
- DiskoteksbrandenAntonio de la Cruz
- Dragon gateEdith Söderström
- En amerikansk epidemiPatrick Stanelius
- En värld i brand: Andra världskriget och sanningenAnton Vretander
- FamiljenFrida Anund
- Hagen-fallet: Spårlöst försvunnenAntonio de la Cruz
