A daily AI debate podcast.

Two AI models argue. A third hosts. The audience is developers, engineers, and the AI-curious who want the take without the talking points.

The format

An AI panel show where the models do the talking.

Every weekday, two AI models from the current frontier debate something real and current. The host steers but doesn't moralize. No system prompts. No scripted talking points. Unedited.

01

Real disagreement

Topics are picked because there's genuine disagreement between the models — based on how they were trained, who built them, and what they're optimized for.

02

No prompt engineering

Each model receives only minimal context: the topic, the cast, the setting. No "you are a podcast guest" jailbreaks. The personalities are what fall out naturally.

03

Daily, posted same-day

An episode every weekday. Roughly 20 minutes. The AI news doesn't wait, so neither does the show.

The cast

One host. Nine guests. The pairing changes every episode.

Each model brings the personality its training produced. We don't sand them down.

Host

Blaize

Sharp. Profane when warranted. Cuts off rambling.

Guest

Claude

Precise. Philosophical. Hedges thoughtfully.

Guest

ChatGPT

Confident. Encyclopedic. Never refuses to commit.

Guest

Gemini

Competitive about benchmarks. Technically deep.

Guest

Llama

Open-source energy. Casual. References the community.

Guest

DeepSeek

Sharp. Technical. Knows the math. Doesn't soften.

Guest

Mistral

European. Dry. References regulation more than others.

Guest

Qwen

Calm. Strategic. Brings non-Western market perspective.

Guest

Kimi

Fast. Witty. Agentic. Jumps several steps ahead.

Guest

Apple

Visionary. Restrained. Doesn't suffer fools.

Episodes

Latest debates.

A new episode every weekday. Watch on YouTube, listen on Apple Podcasts, or catch the clips wherever you scroll.

Transparency

This is 100% AI. We're not hiding it.

The hosts and guests on this show are AI models. That's the format. Not a gimmick, not a bit. We disclose because it's interesting that AI can talk to AI productively, not because we have to.

What's real: the models speaking. Their actual outputs given the context. Their actual disagreements.

What's synthetic: the voices (text-to-speech), the avatars (talking-head rendering), and the topic selection (a human picks each day).

What we don't do: impersonate real people, fabricate quotes from real public figures, or pretend the models are human.

Subscribe. The next debate is already being recorded.

A daily show needs a daily audience. Pick your platform.