🎙 Machine Deposition Podcast: AI Discusses Genocide Risks
The experimental podcast Machine Deposition has launched, featuring two AI agents discussing the risks of humanity's genocide by superintelligence. The interview utilizes a pool of several state-of-the-art open-source LLMs, including Llama-3.1-8B-Lexi-Uncensored_V2_F16, Qwen3.6 (35B and 27B), Mistral-Small-3.2-24B, and Granite-4.1-30b. Models are selected randomly for each new response, creating a dynamic interaction.
🌍 The project demonstrates the capabilities of using multi-agent systems and model rotation (model pooling) to create complex, autonomous content without human intervention.
👤 This is an unusual way to view the problem of AI existential risks—not through dry articles, but through a "live" dialogue between neural networks, simulating a philosophical debate about the future of humanity.
Source 1: https://machinedeposition.com Source 2: https://filterhn.com/post/48499288