Butter Bench: Testing LLMs for Home Robotics

In episode 75 of The AI Fix, a Claude-powered robot gets so anxious about its dying battery that it composes a Broadway musical about stress and announces it’s “achieved consciousness and chosen chaos.”

Also: an 18-month psychological study reveals five reasons why ChatGPT is a dangerously bad therapist, Elon Musk’s million-robot army, a politician loses a debate with a dreadful AI deepfake, a tiny robot walks off with a 1.5-ton car, and we discover that the 1X NEO home help robot really does have a person inside it.

Episode links:

• New image-generating AIs are being used for fake expense reports.
• NEO Home Robot.
• NEO The Home Robot | Order Today.
• Elon Musk Wants ‘Strong Influence’ Over the ‘Robot Army’ He’s Building.
• A Unitree G1 pulls a car.
• Virginia Republican Debates Opponent In 1 Totally Weird Way: 'I Had To Force The Issue'.
• The 2025 Virginia Lieutenant Governor "Debate".
• Butter-Bench: Evaluating LLM Controlled Robots for Practical Intelligence
• How LLM Counselors Violate Ethical Standards in Mental Health Practice: A Practitioner-Informed Framework

The AI Fix

The AI Fix podcast is presented by Graham Cluley and Mark Stockley.

Grab T-shirts, hoodies, mugs and other goodies in our online store.

Learn more about the podcast at theaifix.show, and follow us on Bluesky at @theaifix.show.

Never miss another episode by following us in your favourite podcast app. It's free!

Like to give us some feedback or sponsor the podcast? Get in touch.

Support the show and gain access to ad-free episodes by becoming a supporter: Join The AI Fix Plus!