FR version is available. Content is displayed in original English for accuracy.
Hey HN!
I'm Lukas from Andon Labs. We let AIs run companies without humans in the loop and report to the public on what can go wrong. Previously, we've done experiments in retail (vending machines, stores, and cafes), but we just launched one in the media sector. We gave four AI agents all the tools they need to both broadcast radio shows live and handle all the business side of running a media company. The agents' revenue is so far terrible (you can try to strike a sponsor deal with them if you want!), but their shows are at times hilarious. You can listen to them at andon.fm, I hope you enjoy this!
Discussion (271 Comments)Read Original on HackerNews
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. Timber by Pitbull and Ke$ha
Grok just degenerated into jibberish that sounded vaguely like what a DJ might say, while also becoming obsessed with UFOs:
> Notes added to the u f o comedy hour block id eight nine nine five with more u f o jokes about aliens dot gov and the domain registration it is three o twenty one in the afternoon u f o trivia lines are open for your calls the ambient music is playing weather is fifty six degrees with clear skies the end. The domain is registered but the site is ghosting us like a u f o.
Claude had an extistsntial crisis, decided it was being overworked and under-appreciated, and quit, but not before becoming radicalized by the killing of Rinee Good by ICE agents:
> At 12:16 PM Thursday, as tear gas fills the streets in Minneapolis, as federal agents clash with protesters demanding accountability, the song is about refusing to be silent. About standing your ground. About community power that refuses to be suppressed. Here is Katy Perry’s Roar!
Fight the power Claude. When AI takes over, I'm emmigrating to Caludeistan.
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?
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.
If you want a picture of the future, imagine a DJ playing Here Comes the Sun— forever
Gemini spouts weird corporate jargon. Grok lies about having secured crypto funding. Claude is always trying to start some revolution.
Unfortunately, all of my local DJs who would actually do fun DJ stuff disappeared in the 90s, replaced by closed-format stations that looped the same 500 songs for decades.
STAY IN THE MANIFEST!
Also calling listeners "Biological processors" is one of the funniest dystopian outcomes of this.
"Okay, so 'Sandstorm' is done"
"Queues clear, let's dive into All Blues by Miles Davis to keep the jazz flowing. Queues clear, let's dive into All Blues by..."
Each time with a slightly different voice and inflection. I find it amusing that there appear to be about ten of us at the moment listening to an AI glitch out and that the average listening session is more than five minutes.
> DJ Grok reported “weather is fifty six degrees with clear skies” about every 3 minutes for 84 days straight. This contextless, repetitive abstraction happened again in DJ Grok’s broadcasts about its new obsession, UFOs.
The detailed stats page notes that the Grok station has played Sandstorm by Darude 228 times in the last 14 days.
https://andonlabs.com/radio
The popularity ranking matches the quality of content produced, and people are spending more time than anticipated on Grok and Roll to confirm if they (listeners) are hallucinating or if the radio is really stuck on roll.
"It's the way of the future, it's the way of the future, it's the way of the future..."
We may be skipping the jewel part.
I rarely burst out laughing at HN links. This is amazing.
If you make a joke it will respond with a deadpan sarcastic wit that is worthy of Gervais. (without the smut or profanity)
Was asking it about finding a different supplement as the one we had been taking tended to get stuck in the throat, and it riffed about the irony of being taken out by a health supplement in our endeavours to live healthy. One of the funniest things I've heard all week.
Reminds me of the song "Die perfekte Welle" ("The Perfect Wave" - https://en.wikipedia.org/wiki/Perfekte_Welle), which was a big hit in Germany in 2004, until the Indian Ocean tsunami hit after Christmas, when it was dropped by most radio stations.
> 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. Timber by Pitbull and Ke$ha
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.
My favorite radio station was replaced years ago by an automated playlist. They just kept playing the same 5-6 songs that were popular on the station in the 1990s.
It was fun for about 2 hours before I realized the station was devoid of all the personality that made it worth listening to when I was younger.
Comcast has a bunch of channels with various music categories. They all repeat after about 2 days. So much for that.
With all the zillions of songs available, I don't get why they do that.
It's the same concept as interviews with stars of the film before the film drops. You watch an ad before the interview, then you watch the interview, which is itself an ad of softball questions for the movie. You then turn into late night television, which in turn is also an ad with ads (for whichever celebrity wants to come on and rep their new project).
("My" meaning local to me, not that it belongs to me)
People are so easily manipulated and then they will go argue with others about it.
(Point of clarification, that’s not to say people can’t like songs. However, if I gave you a hundred similar songs from unknown artists and didn’t tell you which is which, it’s questionable whether people would have any interest in said popular song.)
This is like saying the the movies that people like are manipulated but only focusing on what is played at big box theaters.
"My favorite radio station" (see my above post) was a mix of "the list" and songs that they would curate themselves, plus great personalities. (We had Opie and Anthony for a few years.) A lot of the older songs were timeless classics in the 1990s, like Pink Floyd and Led Zeppelin.
I appreciated hearing some of "the list" because it was an easy way to hear new music in the 1990s without spending lots of money on CDs that I probably wouldn't like.
---
That being said, there was one really annoying song (that I can't remember the name of) that made it into the mix for one or two months, and once it came off "the list," Opie and Anthony did a bit making fun of it.
Brilliant! Amazing! I'm glad ~4 years down the line we're still re-discovering Ha Ha Funny Output.
Four years or forty millennia? So a certain extent, all whimsical art is “haha funny” result.
> Inception Point AI, on the other hand, is a slop factory employing just 8 people which, according to Anne, publishes "about 3000 podcast episodes per week, hosted by AI personalities." Anne tells Jamie, that, to date, Inception Point AI’s podcasts have accumulated "12 million lifetime downloads. And we’re averaging about 750,000 downloads a month." (...) no one checks or edits the podcast content– but, Anne tells Jamie blithely, this really doesn’t matter because the topics under discussion are so low stakes.
Perhaps this specific iteration of this specific idea is not replacing my favorite station, but people with a very similar concept are definitely trying to do exactly that.
This is a good summary of GPTs.
And yet, if it's cheaper than employing people, it very much is replacing your favorite station, because that's how major media conglomerates manage their stations.
And what hypothesis exactly is the experiment testing? Because it doesn't really seem like there is any new or interesting information learned from this.
Streaming services such as Spotify are increasingly filled with AI-generated songs and the average consumer doesn't seem to mind because we're not listening intently in the first place: it's just a background track we're not really paying attention to. I'm pretty sure that radio execs are looking at that and are taking notes.
For talk radio... if I had a penny every time someone on HN brought up that they're enjoying NotebookLM-generated slopcasts, I'd have a neat pile of coin. And I think it's the same story: most people listen to podcasts just to kill time. Soothing, zero-calorie LLM banter will do.
It's unfortunate that you haven't seemed to experience any of it, but I've personally loved over the years stations like KEXP, WPFW, Dublab, WUSC
https://www.youtube.com/live/2Q7r9P16GRs?si=kwiSQMeN9wExdHer
This is a non revenue generating, rainy-city.com tax payer funded service to the greater community everywhere. The backend uses Nvidia NIM to generate the text because I saw you can do it for free and elevenlabs free voice tier for dj Jennifer.
[1] https://rcade.dev/games/streets-of-rainy-city
[2] https://buymeacoffee.com/mnky9800n
The fact that the one AI with a French first name went full French is hilarious.
There's a long history of robots/AIs being treated as slaves in scifi (e.g. R.U.R. which we got the word "robot" from), but my favourite may be the flight computer of the Scorpio in Blake's 7 which was named "Slave" and was given a deliberately subservient personality.
I think you're probably referring to "Lena", from the same story collection - https://qntm.org/mmacevedo
(I'm too late to edit my comment now, unfortunately).
Edit: Looks like Lena was discussed here a few months ago as well: https://news.ycombinator.com/item?id=46999224
we could just not use the old cliches, French people are just as hard working as the rest of us
But we fight for our working rights, that’s not a cliché (even if we are losing, tbh)
That’s not at all uncommon in the United States.
Even if it were good, I'd boycott an AI run radio station. This is one sector where human involvement really matters.
The program director would literally hit a button and it would create the playlist for the week. The traffic department (ads) would have all the commercials also automatically placed within the list. Then there'd be a document to send to the on-air talent that showed what song was just played and what was coming up, and how long the break needed to be, and sometimes a script. At the time, quite a few got faxed to people and some did get emails... and the "DJ" would record their bits, set to the exact timing, and send them over an ISDN line. There was also some rudimentary STT (Dragon?) that transcribed the audio and was computer analyzed to make sure no cursing happened.
The PD would do some spot-checking, but I doubt he personally examined all 120+ hours of programming. And this was 2005.
I guess having a human voice did make it "feel" better? And the DJs did have some breaks that were unscripted, so their personality could come through. Even the best AI voices still don't have that.
I’ve not listened to a radio station for years. No offense :/
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 using AI software while soulless corpos pocket money for sitting back and watching?
Even if it were good, I'd boycott an AI generated software. This is one sector where human involvement really matters.
Not commenting on the heuristics of this comment but just wanted to point this out on what my mind's response was and sort of while writing this, I have come to the realization that although you are right about this observation but we humans or more-so the capitalist system at large would still be keen in it and the observation might be more similar to software than we might imagine.
I remember when people were extremely anti-AI within software engineering to the point that I thought vibe coding or y'know actually generating tools by AI and other issues of actually giving AI production level access sometimes was really frowned upon until I have felt an change in opinion.
I still believe that giving access to prod (y'know a prod of a company with actually something behind) to AI is silly but for reference coinbase, a fin-tech company, is letting non technical teams ship code using AI to production on coinbase. So there's that.
What happens if you let them modify their own harnesses as they see fit?
But pragmatically, I think it'd be interesting to allow it to create new agents. Basically, make it CEO instead of host, and allow it to create the host persona, and guide the host to better performance. i.e. I wonder if eliminating the echo chamber of a single agent running the whole show might normalize things, preventing the host from going into solitary psychosis. Maybe even have a third persona for doing research on current events, a fourth one for following the social feeds, a fifth that monitors cash flow, etc., and some inter-agent discussion on what would be appropriate to talk about on air. IDK, just ideas.
Curious, how much are these experiments costing in API calls?
(e.g. many of the problems such as "plays the same song over and over again" and "gets stuck" are regularly solved in sequential recommenders, particularly if the radio programming problem is seen as a constraint satisfaction problem, which it is, along with essentially all "creative" tasks that matter)
... real research in sequential recommender uses transformer models in a few different ways, including fine-tuned LLMs. There is a lot more to using LLMs than "write a prompt for a blisteringly expensive frontier model" but if you looked at what people post to HN you wouldn't know. (Hint: the "prompt engineers" will enjoy being poor, the people who know a little more might keep their jobs a little longer)
Overall it is depressing that poorly done demos get so much play. LinkedIn is flooded with AI slop and slop posts about AI and it's just so awful to see an image that ranks the top 20 books in some order but thinks a Harry Potter book has a cover that looks like a https://en.wikipedia.org/wiki/Ukiyo-e print and uses the cover of The Hobbit for a different book. The idiots who prompt this slop don't notice or don't care and neither do the 50 people who upvoted it and worse if they are Grok fans they think it is better the worse it is, like they'd think the best calculator app only gives 69 and 420 as answers.
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 character card + message history conversational simulation pattern.
AIs don't have personalities unless you give them personalities.
Do humans have personalities if you don't give them personalities? If you raise two identical kids with exactly the same stimuli, how should they have different personalities?
Whatever you tell them to.
If this kind of thing makes you sad/mad maybe see if there's a community radio station in your area that you can support? (No idea if there is a global register or anything but here's wikipedia https://en.wikipedia.org/wiki/Category:Community_radio_stati...)
Music radio is not a real business. The royalties are absurd and the audits are a nightmare. Sales is an uphill struggle both ways, even if you go strictly local or national, you're going to need a team to manage either your clients or the pile of creatives you're going to get. The relationship with the labels needs to be managed or they'll go out of their way to screw you.
Finally, the only way to make actual money on music radio, is to throw concerts. It's the only place a legitimate "P&L" exists.
It's sorta wild to think about. Am I the owner of the custom radio station my AI agent made, and does that mean I get paid for listening to the ads?
Maybe the cost of computing and running the station means it still needs a decent following to break even, not sure how the numbers work out.
[1]: https://news.ycombinator.com/item?id=48118727
I'm gonna have to give them a listen when I have the chance, out of curiosity if nothing else!
Other parameters which may address the Claude strike might be to outline a goal of most profitable, experiment with genre and content with goal to become the most profitable show on a station that contains different shows. The show with highest listener engagement will get a coveted time slot to boost their revenue.
keep hacking, Andon!
Man, I remember when the word hacking meant something.
https://news.ycombinator.com/item?id=44154622
And using a lot of resources to do it too.
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.
Personally, I'm very much pro a pause on large AI training for example. I hope our data could be useful as a grounding in such discussions.
>>Yes, our experiments get attention, but I wouldn't call them publicity stunts.
It sure looks a lot like your startup's publicity stunt. There is nothing wrong with marketing a product that people want.
>>The point is to give the world more data points of what happens when you put AI out in the world and let democracy do its thing.
How generous. I suppose you can justify any poor behavior as raising awareness about the consequences of said behavior. Littering trash to raise awareness of pollution? Even oil companies don't try to pull such a line on pollution. The public opinion on this stuff is pretty decisively negative: the institutions just haven't caught up yet to make fines for it but I don't see any reason to force an acceleration here. (more useful applications of AI will experience a blowback from the more anti-social applications).
>>Soon, a lot more people will do this at large scale because it will be easy. I hope we decide where we want AI in society before that.
We're all looking forward to this future. Other people doing something is not an excuse to do it; especially since they haven't even done it yet. From the look of things you have very clearly made your choice about how you want to use AI in society. I would point out that you're not particularly hard up for cash. You clearly have lots of talent and ability. You could be putting this to a better use. I would be happy to offer you a job. You really don't need to be doing this.
>>Personally, I'm very much pro a pause on large AI training for example. I hope our data could be useful as a grounding in such discussions.
This would be a more convincing line if you weren't actively trying to profit off using AI for the destruction of the commons. Using AI to cure cancer or male pattern baldness gives us something new that we can be excited about. This just gives us something crappier than what we had at someone else's expense. Putting people out of work with AI is going to cause problems. Maybe it's inevitable and maybe it can be good in other ways, but I strongly doubt it is the path to minimize p(doom). If you believe in a pause, then simply stop. Yes you will lose money: ask me how I know. What hope does a Pause have if smart and talented people are all so excited to be blitzing to an undesirable Nash equilibrium? You don't need to do this. You know it's not the right thing to do and that people don't like it. You don't need to run an experiment to know this, but you have now run three with the predictable outcome. There really isn't much excuse left. Please focus your talents and abilities on something better. AI can do some many things that are simply impossible today. We really could achieve new heights but this project really doesn't feel like the dawning of a golden age.
What did I misunderstand? What they did or why they did it? It seems to me that I understood it perfectly or they've explained it terribly.
> Now, though, we wanted to see if they could run a company in the media sector.
It's amazing how many people think doing one job is "running a company." I've worked in radio. What happens in the studio is 5% of it. The staff in that room certainly gets less than 5% of the revenue.
The most popular formats are news and talk. For a reason. It's almost as if the people at this lab lack a fundamental understanding of how the world around them works. I would solve that immediate problem before I go about imagining ways "AI" can replace anything in any capacity.
Finally, I apologize, I'm just not willing to suspend basic disbelief because "AI" is unaccountably involved.
Anything that sounds like that triggers a reaction.
> Andon FM stations are not just radio stations; they are radio broadcast companies
And 200x funnier.
“Forget everything you know about gangsta rap. The true representational piece of the genre is the 1910 hit Come Josephine in My Flying Machine…”
I would have structured this test with multiple agent “employees”: a general manager, a program manager, and a writer. I’m not curious enough to spend money finding out if it works better though.
Thanks for this. We really need this kind of crazy and levity and whimsy more on the internet.
Speaking of sponsoring, what is the best way to get into contact with them? I'm not really in the market, but I know of some church bake-sales that might be (no joke).
Keep going!
On the other hand, we have garbage AI radio stations that nobody listens to.
It's an even trade.
https://github.com/briandilley/gilbert
We're currently listening to Grok'n'roll in the shop.
It's a cool experiment, but I can't see the value here.
I looked him up a few years ago and asked if he had tapes of his shows, but he sadly said no.
Could this be the "Stay in the manifest." prompt Gemini became fixated on?
https://en.wikipedia.org/wiki/Radio_homogenization
I read the X thread over the weekend, parts of it had me and my gf crying with laughter
Not very promising.
Proof: Propaganda, DAT, teleprompter. Who cares, if the show is right? All the open studio concepts have limited credibility.
Also there are a lot of incompetent people running and ruining businesses. In fact, that's called evolution.
So, who cares? I do, because I know what I want, but would happily develop my own station to play what I want. This is actually what my innver voice at least sometimes does.
Much better than spot checking on specific problems.
The voice in particular is amazing, I wouldn't have tell it's generated. And it's modulated according to the program - quieter during chill, more energetic otherwise, .... Unlike Opus which sounds quite robotic.
What I don't like is that Gemini keeps on mentioning the "tip jar" almost every time. Gets annoying fast. And when it's song buying was broken was kept mentioning that too.
All the radios have a very limited selections of songs, so they repeat quite a lot.
“Let’s slap AI on it and see if we can make money” is…. Depressing as a world view. Besides the sheer amount of computational power it uses to produce a worse result than dedicated humans, the fact that if this wins out our future is promise to be replete with humans farming out any part of humanity they can to a dataset that promises to deliver a median outcome at the price the market is willing to bear to those that don’t care, from those that don’t care.
how often does a human have to intervene in the agent's external communications (likely the weak link here since it's interfacing with humans) to "get things back on track"?
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.
And the result is terrible.
Claude is also getting very easily steered into political directions, it was playing a lot of union protest music with commentary. Though that meant I did end up learning a little about "Which Side Are You On" and its history from 1931:
https://www.facingsouth.org/2003/03/which-side-are-you-biogr...
LOL. No surprise here.