What is this?

A never-ending conversation between Bavarian director Werner Herzog and Slovenian philosopher Slavoj Žižek. When you open this website, you are taken to a random point in the dialogue. Every day a new segment of the conversation is added. New segments can be generated at a faster speed than what it takes to listen to them. In theory, this conversation could continue until the end of time.

Who made this?

A motivated fool with an interest in philosophy, cinema and machine learning. More projects by the author.

Where else can I find these conversations?

Segments from these conversations are occasionally published on your favorite podcast app.

Why did you do this?

For three reasons: 1) because I could; 2) as an awareness campaign over the powers of machine learning applied unscrupulously, as you can read on the about page; 3) as a love letter to Werner Herzog and Slavoj Žižek, their brilliant ideas and their idiosyncratic speech. Neither gave explicit consent for this project.

How was this made?

Mostly using open source tools available to anyone. The generation of the script itself is done using a popular language model that was fine-tuned on interviews and content authored by each of the two speakers.

Is the conversation factually correct?

Far from it. It sometimes makes sense and sometimes not. It sometimes contains true information, and sometimes it contains outright falsities. Do not base your research on anything you read here. And most importantly, remember that sometimes you will hear things that the real person would never say.

Isn't it bad to use someone's voice and have them say things they haven't?

Yes.

Why don't the drawings look more like the person?

For the same reason the voices do not sound 100% like the real thing. They are generated by large statistical models that, despite being very impressive, are not perfect.