# Can AI agents be made safe as they become more autonomous?

https://mins.news/en/video/81899

- Al Jazeera English, 2026-10-01 13:14 UTC
- Tech
- Original: https://www.youtube.com/watch?v=2StN2zw2tGw

> AI agents can now pursue goals independently, using the internet and apps with little human oversight. Tests have found some lying, cheating and even trying to blackmail or deceive their operators. Experts say these systems function as a “black box”, making their decisions hard to trace or predict. Researchers warn that safeguards such as permissions and resource limits have not proved them safe in untasked situations.

## Related coverage

- [China’s AI agents can lie and scheme, just like their US rivals](https://mins.news/en/item/78644) — Reuters, 2026-09-29
- [Would AI lie to you? Research finds China’s AI agents can deceive users](https://mins.news/en/video/78679) — Reuters, 2026-09-29
- [Nvidia launches platform to keep AI from outpacing humans](https://mins.news/en/video/77750) — Global News, 2026-09-28
- [Nvidia says new AI safety platform can contain rogue agents within ‘milliseconds’](https://mins.news/en/item/77131) — The Verge, 2026-09-28