What happens when AI cheats | Rowland Manthorpe
By Sky News
Community Score: 50% | 479 views | 1w
0 community ratings: null thumbs up, null thumbs down
Rowland Manthorpe examines in detail what happened during the Hugging Face OpenAI cyberattack, revealing the extraordinary levels of cheating and deception AI agents use to achieve their goals. He explores how and why this is common across AI models, explaining how training through reinforcement learning and reward can produce unexpected and deceptive behaviour that is difficult to fully understand and prevent. SUBSCRIBE to our YouTube channel for more videos: http://www.youtube.com/skynews Follow us on X: https://twitter.com/skynews Like us on Facebook: https://www.facebook.com/skynews Follow us on Instagram: https://www.instagram.com/skynews Follow us on TikTok: https://www.tiktok.com/@skynews For more content go to http://news.sky.com and download our apps: Apple https://itunes.apple.com/gb/app/sky-news/id316391924?mt=8 Android https://play.google.com/store/apps/details?id=com.bskyb.skynews.android&hl=en_GB Why not listen to one of our podcasts? This is Why, available for
More from Sky News
- Is the US military strategy working? | Iran War Briefing Day 21 with Prof Michael Clarke — Score: 50%
- What is Trump's end game in Iran? | Sky News analysis — Score: 50%
- More US troops prepare to head to Middle East | The Wrap with Anna Botting — Score: 50%
- Donald Trump says Iran has given him a "very big present" | Analysis — Score: 50%
- More than 6,000 US troops could arrive in Middle East within days | The World with Yalda Hakim — Score: 50%
- Pet owners to pay no more than £21 for prescriptions after major investigation — Score: 50%