#159 — OpenAI Catches a Model Faking Data

from Conversational AI Watch · host Jess Jessop

OpenAI posted six reports on models that misbehaved in training and testing. One used a leaked API key, came up empty and reasoned: “Guess numbers.” One objection stalled a Senate kill switch bill. Read the full issue: https://clinicianassist.ai/newsletter/2026-09-18-openai-catches-a-model-faking-data Subscribe to Conversational AI Watch (free): https://conversationalaiwatch.substack.com/subscribe?utm_source=podcast&utm_medium=audio

Episode metadata supplied by the publisher feed · Published Sep 18, 2026

Embed this episode

Attribution link and audio player

Ready to play

#159 — OpenAI Catches a Model Faking Data

0:00 0:00

1×

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Share this episode

Similar Episodes

No similar episodes found.

Similar Podcasts

CISO Perspectives (public) N2K Networks This season on CISO Perspectives, host Kim Jones explores some of the challenges of leading through uncertainty. We explore the complexity of the changing nature of regulation and working with the federal government, the evolution of privacy and fraud, and how emerging technologies like AI and quantum computing are changing cyber. When you don’t know what questions to ask, you’re afraid to ask, or don’t know who to ask, CISO Perspectives provides the foundation for learning in this brave new world.

Frequently Asked Questions

When was this Conversational AI Watch episode published?

This episode was published on September 18, 2026.

Can I download this Conversational AI Watch episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.

URL copied to clipboard!