In episode 70 of The AI Fix, our hosts learn that AI makes people more dishonest, Waymo’s robo-cars save lives but get outsmarted by a bathroom mirror, a “rescue” bot slurps up victims head-first, and China shows off a fusion robot arm that can lift ten elephants (or 200,000 pigeons, if you’re scientific about it).
Meanwhile Graham reveals how AIs are tricked into solving CAPTCHAs with fake mouse wiggles, and Mark explains how OpenAI’s “deliberative alignment” works perfectly – until the AI realises it is being watched.
So, nothing to worry about there then…
All this and much more is discussed in the latest edition of “The AI Fix” podcast by Graham Cluley and Mark Stockley.
The AI Fix #70:
AI behaves… until it knows you’re watching
Hosts:
Graham Cluley:
@grahamcluley.com
@
/ grahamcluley
Mark Stockley:
Episode links:
- Japanese rescue robot slurps up humans.
- China’s new robot arm for fusion power plants can lift loads as heavy as 10 elephants.
- Waymo safety report.
- Dr Jon Slotkin tweets.
- Boffins fool a self-driving car by putting mirrors on traffic cones.
- Artificial Intelligence promotes dishonesty.
- ChatGPT Agent Violates Policy and Solves Image CAPTCHAs.
- Video of ChatGPT agent solving image CAPTCHAs.
- Stress Testing Deliberative Alignment for Anti-Scheming Training.
Support the show:
Grab T-shirts, hoodies, mugs and other goodies in our online store.
You can also help the podcast by telling your friends and colleagues about “The AI Fix”, and leaving us a review on Apple Podcasts or Podchaser.
If you would like to further support the podcast, and gain access to ad-free episodes, become a supporter by joining The AI Fix Plus!
Follow us:
Follow the show on Bluesky, or subscribe for free in your favourite podcast app such as Apple Podcasts or Spotify, or visit our website for more information.
