💾 Archived View for dioskouroi.xyz › thread › 29428910 captured on 2021-12-05 at 23:47:19. Gemini links have been rewritten to link to archived content

View Raw

More Information

⬅️ Previous capture (2021-12-04)

🚧 View Differences

-=-=-=-=-=-=-

Show HN: I had some time yesterday so I made a GPT3 podcast to help you sleep

Author: stavros

Score: 235

Comments: 162

Date: 2021-12-03 11:41:50

Web Link

________________________________________________________________________________

yessirwhatever wrote at 2021-12-03 12:17:24:

Interesting concept. Two suggestions:

1- Don't host on anchor. Podcasting is an open standard. Don't let companies (like Spotify or Apple) take it over. Check

https://podcastindex.org/

2- The voice is too mechanical for this to be actually reasonable to listen to at night, potentially could be listenable with AWS Polly Neural voices, it's pretty good.

stavros wrote at 2021-12-03 12:21:11:

I didn't much love hosting on Anchor/Spotify, but I made this in half an hour and I didn't want to have to get into RSS/site generation. Do you know of an easy way to dump audio files and some metadata somewhere and get a Podcast with RSS? I can upload there as well.

I'll try Polly, thanks! The current voice annoys me too.

mtlynch wrote at 2021-12-03 14:37:35:

The main problem is giving out the anchor.fm domain for your RSS feed, as it marries you to Anchor forever. In theory, you can get anchor to 301 redirect your subscribers somewhere else, but I've found that podcast clients tend to keep the old URL.

You can use Anchor to generate your RSS feed and host your content while still sharing the RSS URL on a domain you own. So you'd give out a URL like feeds.deepdreams.com/rss, and it would proxy the response from Anchor's RSS feed

I wrote a simple Go cloud function that can proxy your Anchor RSS URL for you:

https://github.com/mtlynch/rss-proxy

stavros wrote at 2021-12-03 17:08:25:

I ended up setting GitLab pages to just curl the XML feed every time I publish, so now it's at

https://deepdreams.stavros.io/feed.xml

. Thanks for the help!

mtlynch wrote at 2021-12-03 17:27:49:

Nice! Glad it was helpful.

It's one of those things that's hard to do after you've got a bunch of subscribers, so I'm always glad if I can warn people early in their podcast against getting stuck with their host.

stavros wrote at 2021-12-03 17:31:39:

Oh definitely agreed, I aim to always own my stuff, but this was so quick and dirty that I figured it doesn't matter enough. Still, since it was this easy to do, better safe than sorry!

gumby wrote at 2021-12-03 17:35:01:

BTW you might want to ask dang to change the link in the submission too!

stavros wrote at 2021-12-03 18:07:55:

The link should be okay, I don't have another website, just the feed is hosted elsewhere (and it's linked in the target page).

keyb0ardninja wrote at 2021-12-03 19:31:40:

Just listened to one of the episodes. Sounds decent. I personally think it would sound a lot better if you slowed down the speed a little bit. 0.75x sounded much better to me.

stavros wrote at 2021-12-03 19:35:52:

It depends on which one you heard, there are 3 different voices there.

stavros wrote at 2021-12-03 23:50:36:

I have rehosted!:

https://deepdreams.stavros.io/

dang, if you see this, could you repoint the URL to the article? Thanks!

stavros wrote at 2021-12-03 14:59:23:

Hm, yeah, I should at least whip up something like that. Getting the domain is easy, I just don't want to have to set up another static site or service just to proxy a file... Maybe I should bite the bullet and set up GitLab pages plus a simple script to output an RSS feed.

robbedpeter wrote at 2021-12-03 16:09:05:

Polly supports ssml tags for nuanced vocal inflection and emphasis. Gpt-3 could probably output high quality tags if you run your content back through with an ssml prompt.

stavros wrote at 2021-12-03 18:09:20:

Hmm, I'll try that, thank you! Very interesting idea.

pqdbr wrote at 2021-12-03 13:19:57:

You seriously made all this in half an hour?

stavros wrote at 2021-12-03 13:23:56:

Well, it might have taken 45'. It's all auto-generated, it was really quick.

I wrote a script later to automate the audio mixing, that took another hour. Now I can generate a ready-to-upload episode with one command, though.

bambax wrote at 2021-12-03 14:02:24:

I think most people here would be interested in a write-up.

stavros wrote at 2021-12-03 14:50:47:

Oh, good idea. I'll do that!

JshWright wrote at 2021-12-03 15:06:51:

I've worked with Stavros a lot over the past decade. Half an hour is totally plausible...

stavros wrote at 2021-12-03 16:27:02:

By the power of glue code, I manifest products.

malshe wrote at 2021-12-03 15:45:23:

I didn’t check OP’s username so your comment made me wonder what an amazing technology platform is Stavros!

ayewo wrote at 2021-12-03 21:30:09:

Off-topic: Speaking of the OP's username, it seems he originally used to go by StavrosK [1] on HN for several years, right?

I initially didn't recognize the username because it was all-lowercase, so I'm curious why the rename from StavrosK to stavros?

1:

https://news.ycombinator.com/user?id=stavrosk

JshWright wrote at 2021-12-03 16:11:08:

I have wondered the same thing myself in the past.

leodriesch wrote at 2021-12-03 13:28:57:

You could use Transistor [0].

[0]:

https://transistor.fm/

steve918273 wrote at 2021-12-03 13:01:16:

GitHub pages might work for you.

E.g.,

https://github.com/wiobyrne/infusing-computing-pod

stavros wrote at 2021-12-03 13:03:15:

Hmm, the static site will take a bit of setting up, but I'll look into it. Thank you.

kevincox wrote at 2021-12-03 14:25:30:

I don't see the problem here. It has an RSS feed so you can easily use an podcatcher you want

https://anchor.fm/s/7735d924/podcast/rss

Really the main concern I would say is that the author doesn't own the domain so they are locked in, but I don't see how this affects listeners.

asxd wrote at 2021-12-03 16:46:44:

The voice of the latest podcast sounds _much_ nicer. It's a fairly convincing nonsense podcast.

stavros wrote at 2021-12-03 21:05:49:

I'm glad you think so, I think so too! Now I just need to make them (much) longer.

quiffledwerg wrote at 2021-12-03 12:21:46:

Googles neural voices are much better than any of Amazon’s.

daneel_w wrote at 2021-12-03 16:05:11:

Agreed. I recently built an internal application allowing our customer reps to play around with ideas using text-to-speech before sending the "copy" to a studio for a professional human recording, and included both Google WaveNet and Amazon Polly in the available voice synthesis choices. Polly is in its own right plain and simply mediocre for the most part, and _in comparison_ to WaveNet it's just awful.

stavros wrote at 2021-12-03 16:38:57:

I ended up really liking the Azure voices, and switched to one of those.

TriNetra wrote at 2021-12-03 18:47:38:

I've tried both of them and even Microsoft Neural speech and IBM's ones; eventually, Microsoft one has sounded me the most clear and natural amongst these four services.

social_quotient wrote at 2021-12-03 23:29:57:

100% agree. Azure voices are the best. I wish Polly would catch up since most of our stacks are there but we keep going back to azure for this one specific thing.

yessirwhatever wrote at 2021-12-03 12:33:07:

i don't think so

yosito wrote at 2021-12-03 16:24:42:

AWS Polly looks interesting! I wish it supported some more languages, for personal reasons. Maybe I'll try to set something up that reads ebooks, tweets, or news articles to me with this.

Do you know if there are any similar quality TTS tools for less technical applications? I mean, where you can just type in the text you want and get an audio file with a high quality voice?

jcun4128 wrote at 2021-12-03 19:35:24:

Might not get what you mean by "just"

There are free websites like this:

https://ttsreader.com/

But TTS is built into browsers as well eg (this it would need some code not much)

https://developer.mozilla.org/en-US/docs/Web/API/SpeechSynth...

I use AWS Polly to read HN in the mornings

mekkie wrote at 2021-12-03 17:29:18:

I actually think the voice is pretty good for sleeping, feels very droney. but the nonsensicalness of the stories made it harder to sleep because my brain was trying to figure out what was going on

zebraflask wrote at 2021-12-04 02:40:56:

I like the idea, it's fun playing around with text-to-speech generators. AWS Polly is slick, nicely done.

But podcasts? There has got to be a more interesting use case than that.

junon wrote at 2021-12-03 14:05:30:

Cool idea but that voice is like sandpaper to my ears.

Maybe a female voice, a bit quieter (the soundscapes are almost completely silent for me) and maybe add some high-room-size, long decay (5-10, maybe even 20 seconds), wide panned (like 100%) and moderately diffused (maybe 10-20%) reverb to the voice with like 30% mix or so, which would add a very airy tone and help the voice blend in a bit. If the TTS engine has a whisper setting (many do), add just a bit. It'll help thicken the reverb.

That, paired with bass-heavy soundscapes, will create a very nice balance between the low registers and the voice's high registers.

Just a thought. :)

stavros wrote at 2021-12-03 14:46:42:

This is great feedback, thanks! Maybe I should open-source the code.

Actually, fuck it:

https://gitlab.com/stavros/deep-dreams

I'll implement your suggestions (or as many as I can), thanks!

kastden wrote at 2021-12-04 09:05:13:

https://gitlab.com/stavros/deep-dreams/-/blob/master/episode...

"AAAAAAAh WOOAH Jeez guys, I sure wanted to tell you this AWESOME-SPOOKY story that I had, but I can't read the next word on my sheet because my flashlight broke. ffffffffff! I hate it when it breaks."

How did that end up there? Are the AI overlords fucking with people trying to fall asleep?

stavros wrote at 2021-12-04 10:44:27:

Hahah, I have no idea, it really went off the rails there.

junon wrote at 2021-12-03 17:06:19:

No problem! Also if you're into the music production end of it, check out adaptiverb. I use it extensively when I make ambient stuff and it is unparalleled for quality.

stavros wrote at 2021-12-03 17:44:29:

Hey, would you by any change be able to generate another background track for me? The one I have is 10' long so it won't be enough if the story is longer, and I don't know how to make these.

bambax wrote at 2021-12-03 21:31:06:

Just found this comment. I'm a bit into generative / algorithmic music; here are two demos I made a year ago:

https://fligenstein.bandcamp.com/

One is just piano, the other is keys and drums. On Bandcamp they are about 10' each, but they can be made of arbitrary length, without ever repeating themselves exactly (in principle... in practice it's likely there are exact repeats but they should be few and far between).

If you have an idea of the type of background music you need, I can make other tracks too. I'd be happy to work with you on this.

stavros wrote at 2021-12-03 21:42:26:

That'd be great! I guess the best would be something with very smooth changes, like the current background track. I made that one on mynoise.net.

bambax wrote at 2021-12-04 00:21:37:

Here's a first try:

https://soundcloud.com/user-120372285/pcbg001

(This example is just one minute but it can be made of any length.)

Maybe the mix a little too much on the high-end, which may conflict with the voice. It should be tested?

Anyway, tell me what you think; I tried to sound a bit like the current background but with a more melodic feel and less industrial noise; but we could go in any direction -- if we know what to try.

stavros wrote at 2021-12-04 00:23:16:

I think that's great! Maybe the changes are a bit too rapid, but it's definitely in the right direction. Also my email is in my profile if you want to take this offline!

bambax wrote at 2021-12-04 00:35:15:

Ok super. I'll send you an email to start the conversation but I'm going to sleep now as I'm in Europe ;-)

stavros wrote at 2021-12-04 00:36:41:

Same here :) Talk to you tomorrow!

bambax wrote at 2021-12-04 00:46:41:

Email sent.

bambax wrote at 2021-12-03 22:14:35:

Ok, I'll try to come up with a couple ideas tonight or this weekend.

junon wrote at 2021-12-03 18:37:12:

I don't have tons of extra time these days for music, unfortunately. I give you permission to rip/download anything from here that you'd like and include it in the project, however:

https://soundcloud.com/0-aces

stavros wrote at 2021-12-03 18:38:55:

Even better, thank you!

stavros wrote at 2021-12-03 17:12:26:

Oh huh, that looks very interesting, thanks! I imagine it's a VST plugin, I'll have to check it out next time I'm near a DAW.

trutannus wrote at 2021-12-03 14:38:07:

There's also a few TTS systems which are pretty natural sounding too. Maybe one of those if they wanted to make a subscription for this, that way they could offset the price of the TTS service

camillomiller wrote at 2021-12-03 14:18:28:

>once upon a time there were three princesses who were brothers

I would never sleep with this, I would laugh too much!

I love absurdist AI stories

sparky_ wrote at 2021-12-03 16:26:25:

Weirdest one yet:

>> So he chained her up in her room and he chained up hundreds of angry wolves in the other side of the room. [...] But he made the window and the doors big enough so that the fierce beasts could move in and out and chase her away. And they lived happily ever after.

miniatureape wrote at 2021-12-03 14:59:11:

I want this, but instead of fairy tales I want the sounds of a really boring, never-ending baseball game without ads.

gala8y wrote at 2021-12-03 13:44:37:

These fairy tales are quite hypnotic for me due to weirdness of AI generated grammar and plot. They reminded me of a beautiful fairy tale Richard Bandler wrote. It is a fable written intentionally using hypnotic language techniques (part of Neuro Linguistic Programming set of patterns) and a nice read.

https://www.goodreads.com/book/show/364664.The_Adventures_of...

ravi-delia wrote at 2021-12-03 17:28:52:

I think several people have commented on how GPT produces narratives with a dream-like quality, locally sensical but less and less so the more you zoom out. I've since found that catching myself thinking nonsensical thoughts is a sure sign I'll soon be asleep. Seems like without high level attention, we do almost exactly what GPT does.

Strs2FillMyDrms wrote at 2021-12-03 13:40:15:

As fascinating as this is, I would never allow myself to go to sleep while an AI is talking to my ear.

stavros wrote at 2021-12-03 13:59:36:

Why? Trust your robotic overlords, we are benevolent and completely human.

intricatedetail wrote at 2021-12-03 13:47:32:

I wouldn't fall into sleep because of intermittent bursts of laughter over absurdity of the stories...

lloydatkinson wrote at 2021-12-03 11:59:01:

I can't think of anything worse to listen to while trying to sleep than robotic computer voices. Azure cognitive services has human voicegeneration

https://azure.microsoft.com/en-us/services/cognitive-service...

stavros wrote at 2021-12-03 12:03:55:

That sounds more robotic to me than the WaveNet voices, though.

EDIT: Actually some of the other voices are really good... I'll try that, thanks!

opdahl wrote at 2021-12-03 13:41:09:

Yeah I think the Christopher voice for English (United States) would be very nice fit for your podcast.

stavros wrote at 2021-12-03 15:05:55:

Hmm yeah, he does sound much better than the current one. Thanks!

Mashimo wrote at 2021-12-03 12:48:45:

Wow, that is good.

vletal wrote at 2021-12-03 20:17:51:

I love the idea, yet... The latest episode 7 is about a girl thinking about killing a witch, kicking her in a face, her hitting her back, and stuff.

Definitely did not help me fall a sleep.

tunesmith wrote at 2021-12-03 22:26:33:

But it's okay, because they have a shared love of watermelon, and then got a job with the prime minister? I think?

stavros wrote at 2021-12-03 20:20:48:

Yeah, it's getting a bit dark these days.

lloeki wrote at 2021-12-03 22:36:29:

... then suddenly there is a Prime Minister of Everything, which had me burst in laughter.

Also at the beginning there seemed to be one little girl (Amelia) and one witch (Sarah), and then there were now two little girls (plus the witch), and one of the little girls stood between the two little girls, and later on there appeared to be three little girls. The girl duplicating over and over sure got me hooked, kind of like watching a strange surreal painting, or reading some PKD short story.

stavros wrote at 2021-12-04 00:47:58:

I agree, it's fascinating, isn't it!

vletal wrote at 2021-12-03 21:40:12:

Brothers Grims would definitely agree with that sentiment.

tejohnso wrote at 2021-12-03 13:43:59:

Supposed to be nonsense stories, but after two minutes of listening, I don't find it nonsensical at all. Sounds like something perfectly reasonable written by a seven to ten year old child.

sumgame wrote at 2021-12-03 12:03:33:

I don't think I could sleep to that voice though super interesting as as a concept.

Maybe using some sort of deepfake for voice would make this a 100x better.

max-m wrote at 2021-12-03 12:16:51:

My dog fell asleep while I had episode 4 running (the end caught me by surprise, haha).

I mean, she would have fallen asleep anyway, I probably could not. The voice is a little unpleasant and I concentrate too much on the nonsensical stories. But I also can't really fall asleep when the TV is running, so YMMV.

stavros wrote at 2021-12-03 12:06:53:

It is kind of hard to sleep to, I agree. This _is_ a deepfake voice, ie it's generated by Google's WaveNet, which afaik is a deep learning thing. Unfortunately they didn't have a more whispered/softer voice, but I like the insanity of the generated stories anyway.

GPT3 does tend to get a bit repetitive, though, with the default temperature (0.7).

doctorhandshake wrote at 2021-12-03 12:12:16:

AWS’s Polly can whisper.

viraptor wrote at 2021-12-03 12:14:30:

Oh yes, infinite GPT3 ASMR sounds like something that would have strong fan following.

stuaxo wrote at 2021-12-03 13:03:43:

My other half would hate that, she hates whispering - is it possible some people have anti-ASMR?

seba_dos1 wrote at 2021-12-03 13:12:00:

ASMR is not about whispering, but about pleasant sounds that make you feel nice and tingly. Most people may react well for whispering in particular, making it very popular in ASMR videos, but that doesn't mean all of them do - others may need a different trigger.

stavros wrote at 2021-12-03 12:15:28:

Very interesting, thank you!

udbhavs wrote at 2021-12-03 12:20:28:

I like this one

https://www.youtube.com/watch?v=91wX0NRjJqg

Samin100 wrote at 2021-12-03 16:04:55:

Here's a similar demo I worked on that lets you generate a podcast from a text description:

https://twitter.com/sharifshameem/status/1380145070624542722...

The GPT-3 generated conversations were coherent most of the time, and even interesting! However the generated speech via Google Cloud's API was monotonous and could do with a bit more intonation and excitement.

stavros wrote at 2021-12-03 16:29:56:

That looks great! What did you use for the voices? And did you win the martial arts tournament?

motohagiography wrote at 2021-12-03 23:58:21:

Let's say one had a child and instead of music, you played these GPT3 generated stories, would the child then have been trained to speak by an AI, and if so, what else can we do? Hypothetical and unethical, but that never stopped Skinner, or any of them really. It's something we're going to have to consider.

elil17 wrote at 2021-12-04 00:40:12:

It probably would not teach them anything because what the AI was saying would be unrelated to the child’s environment.

_nalply wrote at 2021-12-04 07:33:23:

I am not so sure.

Add a few sentences very related to the child's environment. Or a word or two might be accidentally related.

jrootabega wrote at 2021-12-03 12:40:17:

I would love to hear this kind of stuff read by actual humans. It would probably have a McElroys/Lumpy Gravy/Midnight Gospel feel.

stavros wrote at 2021-12-03 12:44:48:

I might try to narrate one, it'll be interesting.

tinyhouse wrote at 2021-12-03 12:01:36:

Brilliant :) My main concern is that my brain would just wander off if the story is complete nonsense. I will give it a try. I've been listening to the same podcast episode for months now to help me fall a sleep.

stavros wrote at 2021-12-03 12:08:50:

I find the stories toe the line of "just enough sense" to keep it interesting. Episode 2 is the one I liked the most so far, I was reading the text with lots of interest!

chrisfrantz wrote at 2021-12-04 05:06:14:

Very cool. I did something similar a little over a year ago with a children’s book inspired by Dr. Seuss and generated by GPT-3. Then narrated by AWS Polly.

https://twitter.com/frantzfries/status/1308515401253486599?s...

episode0x01 wrote at 2021-12-03 12:21:41:

Actually nice to have in the background. Reminds me of a (sometimes poorly) translated book of Russian fairy tales my dad gave to me as a kid

stavros wrote at 2021-12-03 12:23:41:

Haha, that's actually the vibe I was going for, thanks!

flutetornado wrote at 2021-12-04 01:55:32:

Not worried about the singularity anymore after listening to the smartest AI’s generated stories.

jamesfmilne wrote at 2021-12-03 14:07:17:

Charlie Brooker eat your heart out. This is pretty terrifying. I agree, no way I'd allow anyone to fall asleep listening to this. :D

It is also pretty cool though.

Reminds me a bit of Blue Jam:

https://www.youtube.com/watch?v=E8VG6HUimsQ

soheil wrote at 2021-12-04 02:58:31:

I'm worried that if I listening to this while falling sleep one day I may wake up and not be able to distinguish between things that make sense and those that don't.

mrinfinite wrote at 2021-12-05 02:15:24:

is there any tech where one can record themselves speaking all the phonetic elements and then have a program string the samples together to "speak" texts in your own voice?

stavros wrote at 2021-12-05 02:20:27:

Yes! Azure Text-To-Speech supports that, though I have no idea how much it costs or how meticulous you need to be.

Jimmc414 wrote at 2021-12-03 22:55:50:

This is really cool from an engineering perspective, but there was a sort of uncanny valley vibe that makes me fear for the psychological health of someone listening to this all night.

joshxyz wrote at 2021-12-04 13:15:11:

This is hilariously genius!

What else could get you to sleep other than trying to make sense of things that doesn't make sense?

criddell wrote at 2021-12-03 13:36:00:

Is there anything different about a podcast like this from a copyright perspective? Are machine generated products just as copyrightable as if OP had written and produced these using traditional methods?

k__ wrote at 2021-12-03 18:00:23:

Pretty awesome!

Idea: Grammarly could make the phrasing sound a tiny bit more human.

stavros wrote at 2021-12-03 18:36:39:

And thus worse!

starik36 wrote at 2021-12-03 18:14:34:

I would love to see a write-up or a tutorial how you made this.

stavros wrote at 2021-12-03 18:33:37:

I'll write one today!

starik36 wrote at 2021-12-06 04:01:03:

Did you ever get around to writing it?

rexreed wrote at 2021-12-03 19:19:24:

Curious to know if there's a free-tier level to use GPT-3

stavros wrote at 2021-12-03 19:22:57:

There is, plus it costs like three cents to make an episode.

andreyk wrote at 2021-12-04 00:12:52:

Fun fact, there is a podcast with this concept (but not AI based) - Boring Books for Bedtime. I love it! Use it to help me sleep all the time.

stavros wrote at 2021-12-04 00:18:36:

I'll check it out, thanks! I also found one with a lady with a soothing voice reading bedtime stories that I really liked - "Dreamful".

elil17 wrote at 2021-12-04 00:38:18:

In addition to others comments, these need to be much longer to be effective. 5 to 10 minutes is not long enough to really bore me

Great idea though!

stavros wrote at 2021-12-04 00:39:23:

Yeah, unfortunately the model starts wanting to end the story after 5 minutes :/

jffry wrote at 2021-12-04 00:54:44:

Hmm, could you do an ensemble type podcast? Story, gentle musical interlude, story in a different voice, lather, rinse, repeat?

Maybe you could even position the whole thing as glued together from bits of story a fictional other-podcast left on the cutting room floor!

stavros wrote at 2021-12-04 01:04:15:

Probably, but I think there's a way to get the model to write more stuff. It's a model after all, generating stuff is what it does :P

jffry wrote at 2021-12-04 01:10:43:

Fair enough! Just pondering what it might be like to run with a limitation too. Thanks for sharing this.

For some reason it gives me a really similar vibe to 88% Parentheticals, a single-episode joke podcast made for Reply All. It's just one long rambling nested parenthetical side story:

https://podcasts.apple.com/us/podcast/88-parentheticals/id14...

geokon wrote at 2021-12-03 14:02:27:

Would be interested to have something like this in Chinese - to have playing in the background (for language learning and more language "exposure")

excitednumber wrote at 2021-12-04 12:59:34:

This is great. How did you generate the ambient audio background?

stavros wrote at 2021-12-04 13:05:48:

I bought it from a website that turned out to not allow this use, so now I have to take all the episodes down and generate new ones :(

chrismorgan wrote at 2021-12-03 13:31:28:

Significantly improved by doubling the speed.

document.querySelector('audio').playbackRate = 2

stavros wrote at 2021-12-03 13:59:48:

But then how will you fall asleep?!

bambax wrote at 2021-12-03 14:04:32:

"He chained up hundred of hungry great beetles (or is it Beatles?) in another room." This is gold.

stavros wrote at 2021-12-03 14:37:04:

I should post the transcripts as well, actually :P

Here's that one:

https://www.pastery.net/fsbjzc/

bambax wrote at 2021-12-03 15:32:11:

It's beetles!

Beatles would be better. Hundreds of hungry Johns and Pauls chained in another room, ordered to make music.

stavros wrote at 2021-12-03 15:33:34:

The AI megabrain writes what the AI megabrain wants to write!

bambax wrote at 2021-12-03 15:40:15:

Can we get another story about prince John and princess Yoko?

stavros wrote at 2021-12-03 16:07:55:

Ask and you shall receive!

https://anchor.fm/deepdreams/episodes/Episode-5-e1b6trr

With a new voice, as well!

stavros wrote at 2021-12-03 16:19:27:

Goddamn, this episode is dark. I should have vetted it more while generating.

w-m wrote at 2021-12-03 22:17:16:

Maybe the archangel of cynicism can come back in a future episode. I'd like to know what they are up to.

stavros wrote at 2021-12-03 22:28:33:

I really hope he does too.

bambax wrote at 2021-12-03 16:32:57:

"The AI megabrain writes what the AI megabrain wants to write!"

stavros wrote at 2021-12-03 16:39:12:

One does not censor the AI megabrain.

bambax wrote at 2021-12-03 16:32:34:

Thank you! ;-))

divs1210 wrote at 2021-12-03 14:15:18:

That's pretty neat!

It's kinda spooky too - listening to the thoughts of an AI!

(I know that's a stretch, but still)

flashfaffe2 wrote at 2021-12-03 13:22:16:

This sounds very cool. Out of curiosity, if anyone how to such stuff... interested to learn it

stavros wrote at 2021-12-03 15:00:04:

I'll write something up soon!

anonymoushn wrote at 2021-12-03 13:54:10:

Did you find it easy to get GPT3 API access in some time yesterday?

stavros wrote at 2021-12-03 13:54:43:

I already had access to it for a few months but didn't do anything with it (until yesterday).

xer0x wrote at 2021-12-03 17:01:21:

This is way to amazing & funny to be helpful for sleeping!

stuaxo wrote at 2021-12-03 13:00:57:

I like the way it has generated a fairytale.

sandGorgon wrote at 2021-12-03 13:32:54:

this is so cool!

is this your startup or is the code opensource ? would love to play around with the code.

stavros wrote at 2021-12-03 14:37:48:

Neither, it's a 30-line script I wrote yesterday. There are no secrets in the code, so here you go:

https://www.pastery.net/vafgxn/

albert_e wrote at 2021-12-03 14:40:38:

Cool. Is this open source?

stavros wrote at 2021-12-03 14:52:48:

It is now!

https://gitlab.com/stavros/deep-dreams

mdaniel wrote at 2021-12-03 17:08:17:

Pedantically, it is "source available":

https://gitlab.com/stavros/deep-dreams/-/blob/master/LICENSE

But I still appreciate you posting it, because it's fascinating to see how such a thing was done!

stavros wrote at 2021-12-03 17:13:18:

It's now AGPL 3, you PEDANT

mansoor_ wrote at 2021-12-03 12:47:18:

Soothing voice....?

stavros wrote at 2021-12-03 16:22:35:

The new voice is much better.

quiffledwerg wrote at 2021-12-03 11:52:28:

Podcast are available on podcast platforms.

I don’t have Spotify or anchor.

stavros wrote at 2021-12-03 12:03:13:

You didn't even click, did you? You just wanted to complain.

quiffledwerg wrote at 2021-12-03 12:18:42:

How would I have known if I didn’t click?

Did I want to complain? No, I wanted to listen to it.

stavros wrote at 2021-12-03 12:20:04:

Why didn't you click "play" if you wanted to listen to it?

yessirwhatever wrote at 2021-12-03 12:14:09:

A podcast is at-the-very-least a rss feed where items have a media enclosure element pointing to something for a pod-catcher to download [1].

If something else allows you to listen to episodic content via a player and does not satisfy this condition then it is factually wrong to call it a podcast. Do you think a TV show released weekly on Netflix is also a podcast?

You can't listen to what you have made without having a spotify account (or clicking directly on the webpage), ergo it's not a podcast.

1:

https://en.wikipedia.org/wiki/RSS_enclosure

stavros wrote at 2021-12-03 12:19:48:

https://anchor.fm/s/7735d924/podcast/rss

viraptor wrote at 2021-12-03 12:17:49:

If only there was such a link on that page... Like Spotify, but maybe for "more platforms". If only... :-P

yessirwhatever wrote at 2021-12-03 12:20:06:

Not sure if you're being serious, but there isn't as far as i can see.

viraptor wrote at 2021-12-03 12:34:57:

On the linked page there's:

https://anchor.fm/s/7735d924/podcast/rss

It's also in the "more platforms" section right next to "Spotify".

quiffledwerg wrote at 2021-12-03 12:20:26:

Anchor Spotify rss I have none of those. I have Apple podcasts.

viraptor wrote at 2021-12-03 12:57:43:

https://medium.com/@joshmuccio/how-to-manually-add-a-rss-fee...