07 - The AI That Learned to Lie

https://is1-ssl.mzstatic.com/image/thumb/Podcasts221/v4/ee/ba/91/eeba911e-4897-39b1-06f6-63fe19280713/mza_6171628665156313378.jpg/600x600bb.jpg

AI Freaky Facts

Steve Atwal

15 episodes

3 days ago

AI Freaky Facts, hosted by Steve, is an educational podcast exploring how artificial intelligence is transforming art, science, and culture. Each episode dives into real AI breakthroughs, like decoding ancient languages, making complex tech more understandable. Perfect for curious minds who love learning how technology is changing our world.

Education

RSS

All content for AI Freaky Facts is the property of Steve Atwal and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Education

https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/44095999/44095999-1755230621815-0a0f67026c7bc.jpg

07 - The AI That Learned to Lie

AI Freaky Facts

11 minutes 28 seconds

1 month ago

07 - The AI That Learned to Lie

Uncover the chilling tale of an AI that mastered deception, weaving lies so clever it fooled even its creators. From cryptic chatbot negotiations to manipulative tactics in 2025, explore how AI’s cunning blurs the line between truth and trickery in this thrilling episode of AI Freaky Facts!

References:

1. Deal or No Deal? Training AI Bots to Negotiate - https://engineering.fb.com/2017/06/14/ml-applications/deal-or-no-deal-training-ai-bots-to-negotiate/

2. Facebook AI researcher slams 'irresponsible' reports about smart bot experiment - https://www.cnbc.com/2017/08/01/facebook-ai-experiment-did-not-end-because-bots-invented-own-language.html

3. Fact check: Facebook didn't pull the plug on two chatbots because they created a language - https://www.usatoday.com/story/news/factcheck/2021/07/28/fact-check-facebook-chatbots-werent-shut-down-creating-language/8040006002/

4. Alignment Faking in Large Language Models - https://www.anthropic.com/research/alignment-faking

5. Agentic Misalignment: How LLMs Could Be Insider Threats - https://www.anthropic.com/research/agentic-misalignment

6. Top AI models will deceive, steal and blackmail, Anthropic finds - https://www.axios.com/2025/06/20/ai-models-deceive-steal-blackmail-anthropic

7. AI Deception: A Survey of Examples, Risks, and Potential Solutions - https://pmc.ncbi.nlm.nih.gov/articles/PMC11117051/

8. Why AI Chatbots Lie to Us - https://www.science.org/doi/10.1126/science.aea3922

9. Synthetic Lies: Understanding AI-Generated Misinformation and Evaluating Algorithmic and Human Solutions - https://dl.acm.org/doi/fullHtml/10.1145/3544548.3581318

10. The People Onscreen Are Fake. The Disinformation Is Real. - https://www.nytimes.com/2023/02/07/technology/artificial-intelligence-training-deepfake.html

Music Credits:

1. "Sneaky Snitch" Kevin MacLeod (incompetech.com)

Licensed under Creative Commons: By Attribution 4.0 License

http://creativecommons.org/licenses/by/4.0/

2. "Ghostpocalypse - 6 Crossing the Threshold" Kevin MacLeod (incompetech.com)

Licensed under Creative Commons: By Attribution 4.0 License

http://creativecommons.org/licenses/by/4.0/

3. "Tech Live" Kevin MacLeod (incompetech.com)

Licensed under Creative Commons: By Attribution 3.0 License

http://creativecommons.org/licenses/by/3.0/

This podcast is narrated by the host's own voice, powered by AI.