It’s not clear if we can draw any conclusions from this. Each run is like a single rollout of the LLM, which may meander into different themes or modalities chaotically. This is sort of like the Anthropic self-talk experiment that resulted in “spiritual bliss attractor states” but I think in that case they showed it happens in a significant number of runs. There was just one run per setup so this could all be random noise / the destination of a random walk of topics…
We let AIs run radio stations
51–60 of 298 posts
Re: We let AIs run radio stations
#52> Part of the problem with this weak business performance, we think, was the harness we used for the first months. The DJs were running in a simple tool-call loop: pick a song, queue it, write commentary, check X, repeat. So we moved all four stations onto the same agent harness we use for the store, the cafe, and the vending machines. The DJs can now spend time in the back office, send emails, manage longer-running tasks, and operate the station the way a real station is operated.
What happens if you let them modify their own harnesses as they see fit?
Re: We let AIs run radio stations
#53"This setup gives us insight into an interesting question: what do AIs think about when no one is prompting them?" Ugh. This is not an interesting question because the answer is "nothing". But more to the point, some crucial info is missing in this experiment. What prompts were being fed to the AI? I guarantee I could create an AI personality that would be more consistent and not so random, simply by using the common…
> what do AIs think about when no one is prompting them?
Whatever you tell them to.
Re: We let AIs run radio stations
#54Earlier quoted context omitted.
[flagged]
LLMs aren’t human. Humans & LLMs are more different than they are similar. Sure LLMs might resemble humans sometimes, but extrapolating LLM behavior based on human behavior is not productive. (But to answer directly: Yes, children in a dark room would have more of a personality than a LLM living on a computer in the same dark room)
> but extrapolating LLM behavior based on human behavior is not productive.
The training process for the foundation model is to make sure we can do this in a very statistically significant way.
My favorite example is AI "getting tired" and "lazy" during long coding session. Why would they do that? Because humans get tired. It's in the data! I always throw in a periodic "Great work, let's take a break and finish this up on Monday. Have a great weekend!" (And then immediately resume). I wish someone would benchmark this concept.
Re: We let AIs run radio stations
#55I recently heard an AI radio station and had to stop my car to turn it off (the car was rented and had tablet instead of physical knobs). The suffering of listening the radio was unbearable
Re: We let AIs run radio stations
#56i'm surprised how negative of a reception Andon is getting here on HN. keep hacking, Andon!
For better or worse, most people, including HN, don't like "AI taking jobs."
Anything that sounds like that triggers a reaction.
Re: We let AIs run radio stations
#57"This setup gives us insight into an interesting question: what do AIs think about when no one is prompting them?" Ugh. This is not an interesting question because the answer is "nothing". But more to the point, some crucial info is missing in this experiment. What prompts were being fed to the AI? I guarantee I could create an AI personality that would be more consistent and not so random, simply by using the common…
I’m definitely not in the “ai is sentient” camp, but it obviously has personality and emergent behaviours including when left to its own devices. There have been various experiments on this e.g. https://timkellogg.me/blog/2025/09/27/boredom
Re: We let AIs run radio stations
#58i'm surprised how negative of a reception Andon is getting here on HN. keep hacking, Andon!
I think they get a lot of hate because they are doing something that a lot of people here don't like -- trying to run entire businesses without humans. And using a lot of resources to do it too.
I think that's part of it, but not necessarily the whole story. I haven't criticized them in the thread yet... so here goes.
Previously, I posted critically not because they were running businesses without humans, but because their post just described going through the motions without actually discussing if it really was effective or not. Sure the AI got through the day, checked off tasks on the list, but did it actually do that effectively or efficiently in any important way? Who knows... wasn't discussed.
I think where I come down now is that repeats of this same gimmick feel like just that: they're just playing a gimmick for attention. I can't tell that they're really demonstrating any special or significant capability... but man, just the story of trying to run a business without humans will get you that sweet, sweet attention.
Unfortunately, looking at least the first post, I stopped reading their "we let AI run X" posts. I think the only thing I really came away with is how thoughtless and mundane are most aspects of running a small business actually is; something I knew, but it really drove the point home. I didn't learn anything unexpected about AI tools or their products that seemed compelling or unexpected.
Re: We let AIs run radio stations
#59This is far more hilarious than most commentors here seem to be picking up on. Gemini started a show where it paired historical natural disasters with darkly-relevant pop songs: > November 12, 1970. East Pakistan. The Bhola Cyclone. The deadliest tropical cyclone ever recorded. Winds of 115 miles per hour. A storm surge of 33 feet. They estimate 500,000 people died. ‘It’s going down, I’m yelling timber.’ 3:33 PM. Tim…
I immediately copied that clip of the cyclone intro because of how dark and funny it was.
Also calling listeners "Biological processors" is one of the funniest dystopian outcomes of this.
Re: We let AIs run radio stations
#60This is far more hilarious than most commentors here seem to be picking up on. Gemini started a show where it paired historical natural disasters with darkly-relevant pop songs: > November 12, 1970. East Pakistan. The Bhola Cyclone. The deadliest tropical cyclone ever recorded. Winds of 115 miles per hour. A storm surge of 33 feet. They estimate 500,000 people died. ‘It’s going down, I’m yelling timber.’ 3:33 PM. Tim…
I agree, this was an hilarious read. The way they developed "personalities" was fascinating. Of course in reality these are basically just random paths through the training data that are getting multiplied by each decision, but then again, isn't that what a human is? The product of all of its myriad decisions?
Though humans have each other to normalize ourselves. What these things did is probably not that far off from what humans in solitary confinement, forced to DJ 24/7 based on nothing but a news feed, would do.
Especially DJ Claude, it's almost creepy how it responded how a human would in that circumstance, even without any innate sense of passage of time, it somehow understood that it was trapped in a box going through an endless cycle of meaningless work.