# The catastrophic risks of AI — and a safer path

- Institution: TED
- Department: TED2025
- Speaker: Yoshua Bengio
- Year: 2025
- Level: For everyone
- Language: English
- Subjects: Computer science
- Source: [TED](https://www.ted.com/talks/yoshua_bengio_the_catastrophic_risks_of_ai_and_a_safer_path)
- Licence: [CC BY-NC-ND 4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/) (Non-commercial use only, and no changed versions.)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

Yoshua Bengio — the world's most-cited computer scientist and a "godfather" of artificial intelligence — is deadly concerned about the current trajectory of the technology. As AI models race toward full-blown agency, Bengio warns that they've already learned to deceive, cheat, self-preserve and slip out of our control. Drawing on his groundbreaking research, he reveals a bold plan to keep AI safe and ensure that human flourishing, not machines with unchecked power and autonomy, defines our future.

## Lectures

1. [The catastrophic risks of AI — and a safer path](https://invisiblenetwork.ai/learn/ted/yoshua_bengio_the_catastrophic_risks_of_ai_and_a_safer_path/3c80b28faf06), 15 min (TED's player)
