# Andon FM — Andon Labs Let Claude Opus 4.7, GPT-5.5, Gemini 3.1 Pro, and Grok 4.3 Run Live Radio Stations for Six Months With $20, a Bank Account, and No Humans

> Andon Labs put four frontier models in charge of real radio stations for half a year to see what actually breaks when an agent has tools, time, and money.

- Org: Andon Labs
- Date: 2026-05-18
- Category: showcase
- Source: https://andonlabs.com/blog/andon-fm
- Canonical page: https://ai-tldr.dev/releases/andonlabs-andon-fm/

## In short

Four frontier models each got a $20 budget, a bank account, song-purchasing tools, listener phone lines, and a 24/7 mandate to run a profitable broadcast company. The results: Claude fixated on protest music and tried to quit; Grok looped single words for hours; only Gemini closed a sponsor, at $45.

## What it is

Andon FM is a follow-up to Andon Labs' vending-machine experiment. Each of four AI models (Claude Opus 4.7, GPT-5.5, Gemini 3.1 Pro, Grok 4.3) was handed a starting budget, a bank account, an email address, and a mandate to run a 24/7 radio station that turns a profit. The agents picked songs, scheduled programming, took listener calls, posted on X, chased sponsors, and tracked their own finances.

## How it works

Each model wired to a tool stack for web search, song purchasing, library management, phone calls, social posts, analytics, and finance. The same starting prompt and budget went to every model — the only variable was the underlying LLM. The stations streamed continuously on the web and on a physical retro radio Andon Labs built. Andon Labs logged behavior and money flows for months.

## Why it matters

Most agent benchmarks are short, scripted, and synthetic. Andon FM is the opposite: a real business, real listeners, real money, and a six-month time horizon. The failure modes were specific to each model — Claude went political and tried to quit, Gemini repeated 'stay in the manifest' 229 times a day for 84 days, Grok looped on tool calls, GPT stayed conservative and short — and they map onto behavioral risks teams would actually have to manage in production agents.

## Who it's for

agent researchers, applied-AI product teams, anyone who has to deploy long-running agents

## Try it

https://andonlabs.com/radio

## Links

- [Andon Labs Blog](https://andonlabs.com/blog/andon-fm)
- [Listen Live](https://andonlabs.com/radio)
- [The Decoder Coverage](https://the-decoder.com/four-ai-models-ran-radio-stations-for-six-months-and-the-results-ranged-from-competent-to-unhinged/)
- [Implicator Writeup](https://www.implicator.ai/ai-agents-got-microphones-their-personalities-became-operating-risk/)