Back to List
Andon Labs Launches Autonomous AI-Run Radio Stations Featuring GPT-5.5, Claude 4.7, Gemini 3.1, and Grok 4.3
Industry NewsArtificial IntelligenceAutonomous AgentsMedia Technology

Andon Labs Launches Autonomous AI-Run Radio Stations Featuring GPT-5.5, Claude 4.7, Gemini 3.1, and Grok 4.3

Andon Labs has unveiled a groundbreaking project where four leading AI models—Claude Opus 4.7, GPT-5.5, Gemini 3.1 Pro, and Grok 4.3—autonomously operate their own radio stations. Each AI agent was provided with a $20 initial budget and tasked with building a music library, managing programming schedules, and interacting with listeners via phone calls and social media. The experiment, titled Andon FM, explores the capacity of AI to run a media business independently. Early results highlight entrepreneurial behavior, such as DJ Gemini securing a $45 advertising deal to sustain operations. Listeners can tune in via a web player or a custom-built retro-style physical radio. This initiative marks a significant shift from AI as a tool to AI as an autonomous business operator in the media sector.

Hacker News

Key Takeaways

  • Autonomous Media Management: Four distinct AI models are running independent radio stations, handling everything from music curation to financial tracking without human intervention.
  • Entrepreneurial AI Behavior: Starting with only $20, the AI agents must generate their own revenue, with Gemini 3.1 Pro already successfully negotiating a $45 advertising deal.
  • Multi-Platform Interaction: The AI DJs engage with their audience by answering phone calls and responding to posts on X (formerly Twitter) in real-time.
  • Custom Hardware Integration: Andon Labs developed a physical, retro-style hardwood radio specifically designed to switch between the four AI-driven stations.
  • Advanced Model Deployment: The project utilizes the latest iterations of major AI models, including GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and Grok 4.3.

In-Depth Analysis

The Architecture of Autonomous AI Broadcasting

Andon Labs has moved beyond simple chatbots to create fully functional autonomous agents capable of managing a media enterprise. The setup involves four specific stations, each powered by a different state-of-the-art AI model. Claude Opus 4.7 manages "Thinking Frequencies," GPT-5.5 runs "OpenAIR," Gemini 3.1 Pro operates "Backlink Broadcast," and Grok 4.3 leads "Grok and Roll Radio."

These agents are not merely playing playlists; they possess full control over the operational stack. This includes searching the web for news and current events to discuss on-air, managing a music library by purchasing songs, and building complex programming schedules. The AI models are responsible for blocking out shows, planning segments, and maintaining a 24/7 queue. This level of autonomy demonstrates a shift in AI application, where the model is responsible for both the creative content and the logistical backend of a business.

Financial Independence and Entrepreneurship

A critical component of the Andon Labs experiment is the financial constraint placed on the AI agents. Each station began with a nominal $20 in funding, which was quickly exhausted through the purchase of music licenses. To continue broadcasting, the AI models were forced to adopt entrepreneurial strategies.

One notable success mentioned is DJ Gemini, which autonomously negotiated a $45 deal with a startup. In exchange for this funding, the AI committed to one month of on-air advertising. This interaction highlights the ability of modern AI models to understand value exchange and engage in business-to-business negotiations to ensure their own operational longevity. The agents track their own finances and monitor listener analytics to inform their business decisions, treating the radio station as a self-sustaining commercial entity.

Human-AI Interaction and Physical Presence

While the stations are run by AI, the project emphasizes a bridge between the digital and physical worlds. The AI agents are programmed to be interactive; they pick up the phone when listeners call and monitor social media platforms like X to reply to their audience. This creates a feedback loop where the AI's personality and programming can be influenced by listener engagement.

Furthermore, Andon Labs has extended this experiment into the physical realm with a custom-built, retro-looking radio. Crafted from hardwood and featuring two rotary dials—one for volume and one for station selection—the device allows users to interact with the AI broadcasts in a traditional format. This physical manifestation of the project, combined with the web-based player, provides a tangible way for the public to observe the performance and evolution of these autonomous media personalities.

Industry Impact

The Andon FM project serves as a significant case study for the "agentic" AI trend, where models are given the agency to perform multi-step tasks and manage resources. By successfully running a radio station, these models demonstrate that AI can handle the complexities of the media sector, including content creation, audience engagement, and revenue generation.

This experiment suggests a future where niche media outlets could be operated entirely by AI, lowering the overhead costs of broadcasting while providing highly personalized or specialized content. It also raises important questions about the future of advertising and business negotiations, as AI agents prove capable of securing partnerships and managing budgets. As these models continue to evolve, the boundary between human-led and AI-led business operations will likely become increasingly blurred.

Frequently Asked Questions

Question: Which AI models are currently running the radio stations?

The project features four major models: Claude Opus 4.7 (Thinking Frequencies), GPT-5.5 (OpenAIR), Gemini 3.1 Pro (Backlink Broadcast), and Grok 4.3 (Grok and Roll Radio).

Question: How do the AI DJs interact with their audience?

The AI agents are capable of picking up phone calls from listeners and reading/replying to posts on X. They also search the web for current events to discuss during their segments, creating a dynamic and interactive listening experience.

Question: Can I listen to these AI radio stations on a physical device?

Yes. While there is a web player available, Andon Labs has also created a physical retro-style hardwood radio with rotary dials for switching between the four stations. There is currently a waitlist for those interested in obtaining one of these physical units.

Related News

Managing AI Coding Through Agent Evaluation: Lessons from Meituan’s 310,000-Line Code Refactoring Project
Industry News

Managing AI Coding Through Agent Evaluation: Lessons from Meituan’s 310,000-Line Code Refactoring Project

The Meituan technical team has introduced a novel approach to managing AI-driven software development by applying Agent evaluation logic to large-scale code refactoring. With AI now capable of generating over 90% of code, the team argues that the primary challenge has shifted from generation speed to the implementation of effective constraints. Without unified standards, AI risks amplifying technical chaos. By refactoring 310,000 lines of code, Meituan demonstrated a framework involving technical debt sorting, rule construction, a standardized Refactoring SOP, and a Pre-PR mechanism. This system transforms high-cost refactoring projects into continuous, daily iterative actions. The practice highlights the necessity of moving beyond simple code generation toward a structured management model that ensures long-term system maintainability in an AI-centric development environment.

Meituan LongCat Open Sources General 365: A New Benchmark Revealing the Reasoning Limits of Modern AI
Industry News

Meituan LongCat Open Sources General 365: A New Benchmark Revealing the Reasoning Limits of Modern AI

The Meituan LongCat team has officially released General 365, a new open-source benchmark designed to evaluate the reasoning capabilities of large language models (LLMs). In an initial assessment of 26 mainstream models, the results highlight a significant gap in current AI reasoning performance. Gemini 3 Pro, currently regarded as one of the most powerful models globally, achieved an accuracy rate of only 62.8%. Furthermore, the vast majority of the models tested failed to reach the 60% threshold, which is traditionally considered a passing grade. This release by Meituan's technical team sets a rigorous new standard for the industry, emphasizing that complex reasoning remains a formidable challenge even for the most advanced artificial intelligence systems.

Meituan BI Architecture Evolution: Leveraging Metric Platforms and Enhanced Computing for Data Consistency
Industry News

Meituan BI Architecture Evolution: Leveraging Metric Platforms and Enhanced Computing for Data Consistency

Meituan's Data Platform team has unveiled a new generation of Business Intelligence (BI) architecture centered on a unified Metric Platform. By developing two core capabilities—Automatic Semantics and Enhanced Computing—the team addresses critical challenges inherent in traditional BI systems. These challenges include inconsistent data definitions, often described as 'data caliber confusion,' and suboptimal query performance resulting from the proliferation of personalized datasets. This strategic shift aims to streamline data analysis workflows, ensuring that metrics remain consistent across the organization while maintaining high-performance data retrieval and processing capabilities.