Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

We let AIs run radio stations

andonlabs.com

Post reply on HN
Print view View original

81–90 of 298 posts

Re: We let AIs run radio stations

#81

Post by 6stringmerc »

On God this is some of the funniest shit I’ve ever read in 2026 via HN! It’s the best “anti-tisement” for LLM utility - even a CHILD could do better. Like maybe a control group of four 10 year olds.

The average listening time is the absolute “tell” because that’s not even a fraction of a typical radio station between ad breaks here in Dallas. Granted I mostly listen to WRR Classical 101 - now 100% community funded (myself included). I listened to “Encouragement” (title translated from French, Spanish composer, two guitars) and it was 7 plus minutes alone.

The dialog is unreal y’all, this is a wonderful experiment and lesson in failure, because I’m pretty sure if it was possible, sales of your “radio” until would be in the negative quantity range. I mean, you could give them away and they’d still be returned. Hat tip to former accordion repo man Weird Al for context.

LMFAO thank you for sharing. Signed, 30 year guitarist, 20 year music producer, and 15 year D&B DJ. Just wow.

Re: We let AIs run radio stations

#82

Post by Forgeties79 »

analogpixel wrote: post #72
IdiotSavage wrote: post #17

Guys, this is not replacing your favorite station, you don't have to listen to it. It's an experiment. If you scroll down a bit, there are various audio snippets of interesting dialogue the models produced. I think it's interesting to see in which ways the models fail and that they actually produce some good stuff once in a while.

How is this any worse than I Heart Radio? You can have your radio experience pushed to you by a major corporation, or an LLM.

iHeartRadio is not doing anything. A person at iHeartRadio is doing the work. Even if it’s automated, at some point a person handled it.

Re: We let AIs run radio stations

#83

Post by nomel »

the_af wrote: post #67
nomel wrote: post #54

Earlier quoted context omitted.

> 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…

> My favorite example is AI "getting tired" and "lazy" during long coding session Never seen this even once , nor anyone I know ever reported this. Do you have an example?

First I saw it was Claude Opus 3.7. Had a very long back and fourth about some code, I pointed out an error, and Claude responded "That's what I get for programming at 2am", with the output being filled with "... code here ..." type shortcuts, basically no ability to one-shot a whole implementation anymore. The conversation length WAS reasonably into the 2am range, if it were real. Thought about it, did the statistical trick where I tell it to "have some rest, take a day off!" then immediately follow up with "Ready to continue?", with the next response having no shortcuts, with full implementation, and much better quality. These are trained on human text. This is the human norm, so I always find it interesting when human like behaviors, very broadly present in the statistics, come out like this.

I also see it a little with Opus 4.7, with Claude Code, with the hint being much more terse planning text, that borderlines unhelpful. I put some "rest" in the context to push the latent space closer to what's in the statistics of the training data: a well rested human.

Re: We let AIs run radio stations

#85

Post by rblatz »

the_af wrote: post #67
nomel wrote: post #54

Earlier quoted context omitted.

> 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…

> My favorite example is AI "getting tired" and "lazy" during long coding session Never seen this even once , nor anyone I know ever reported this. Do you have an example?

I see laziness all the time, Claude will be helping me plan work and then it will ask me how a piece of code is implemented. I then have the choice of manually verifying how it works, or to tell it to look for itself. Ideally it would just look without being told.

Re: We let AIs run radio stations

#86

Post by crooked-v »

paulhebert wrote: post #66
48terry wrote: post #30

Earlier quoted context omitted.

Experiment: "We got AI to do things and it did weird stuff sometimes". Brilliant! Amazing! I'm glad ~4 years down the line we're still re-discovering Ha Ha Funny Output.

Yea what are they trying to test? Where is the hypothesis?

They're trying to test if it's good enough to replaced the few remaining paid radio/streaming DJs yet.

Re: We let AIs run radio stations

#87

Post by miltonlost »

AirMax98 wrote: post #73
beloch wrote: post #62

What would have happened if AI had actually been good at this? A bunch of humans would be out of work and the rest of us would be listening to AI radio stations while soulless corpos pocket money for sitting back and watching? Even if it were good, I'd boycott an AI run radio station. This is one sector where human involvement really matters.

I hear you — but what do you think Spotify or any of the other streaming services are? In my mind, algorithmic streaming services have much more in common with this "experiment" than your local radio DJ.

Apple Music actually has radio stations with real humans picking songs. So not all streaming is algorithm if you look.

Re: We let AIs run radio stations

#89

Post by the_af »

nomel wrote: post #83
the_af wrote: post #67

Earlier quoted context omitted.

> My favorite example is AI "getting tired" and "lazy" during long coding session Never seen this even once , nor anyone I know ever reported this. Do you have an example?

First I saw it was Claude Opus 3.7. Had a very long back and fourth about some code, I pointed out an error, and Claude responded "That's what I get for programming at 2am", with the output being filled with "... code here ..." type shortcuts, basically no ability to one-shot a whole implementation anymore. The conversation length WAS reasonably into the 2am range, if it were real. Thought about it, did the statistic…

How do you know you're not reading things that aren't there? LLMs are very good at roleplaying, and they will pick up on hints you may inadvertently be giving them (about them being "tired" and needing "rest", etc).

I have never witnessed this of Claude Opus, by the way. They do get context rot, but that's a relatively better understood phenomenon unrelated to personality.

Re: We let AIs run radio stations

#90

Post by analogpixel »

Forgeties79 wrote: post #82
analogpixel wrote: post #72

Earlier quoted context omitted.

How is this any worse than I Heart Radio? You can have your radio experience pushed to you by a major corporation, or an LLM.

iHeartRadio is not doing anything. A person at iHeartRadio is doing the work. Even if it’s automated, at some point a person handled it.

A person at IHeartRadio is doing the work the corporation tells them to do. do you think they want to play Hotel California on loop all day long?
Post reply on HN