EniasCailliau

Thank for the recommendation! Will check it out.

Not really my point. My point is that it's weird that payment processors ban NSFW content from AI companions

Probably "against the Christian morality of our VISA/Mastercard overlords".

Did they get traction? Is it a viable product? Sounds like it's hard to navigate what is allowed and not allowed as a comp.

Do you think it's more appropriate for me to rebrand to AI_Companion?

Me too. That's why I wanted to turn it more open source. So many companies are already monetising this relatively simple agent model.

What's the plot of the movie? Never watched it.

Yea. Would you be interested if I connect it to a local LLM so convo's stay private? Any good models you have in mind?

Wow. Missed this update. Thanks for sharing!

What if it helps them gain confidence? You could see a AI companion as a safe space to explore social interaction.

Have you tried AutoGPT? I've heard that it can do a bit more through iteration. Haven't tried it out yet for coding hard problems.

My idea too. I hope people can use it to cure their loneliness in the short term and train their social skills in a safe environment so they are more confident.

Got inspired by sites like https://www.konjer.xyz/ and wanted to enable anyone to build websites like these. Launching this today so any feedback is more than welcome!

I'm currently reading the almanack of Naval Ravikant and used it to chat and reflect about the book. Here's my demo: https://ask-my-book.steamship.com/?dbId=cafff4af7828a4436d08...

I struggled with web UI before forcing me to use Streamlit. This fixes that do that I can stand out next to the web dev’s launching AI projects. Excited for this launch!

Stack:

* Transcription: AssemblyAI

* Language AI: OneAI, AssemblyAI, and Huggingface

* Database: Steamship

* Deployment: Steamship

* UI: Streamlit

Thanks! Looks like an alternative would be to create a webpage that includes the streamlit app in an iframe.

Thanks for flagging! Looks like Hacker News does not allow me to post streamlit url's

Stack:

* Transcription: AssemblyAI

* Language AI: OneAI, AssemblyAI, and Huggingface

* Database: Steamship

* Deployment: Steamship

* UI: Streamlit

Time for YT to up their caption game.

Good idea!

That's probably true. I guess we have to start somewhere. I do agree with thimm I often reference a podcast but forgot which one. Being able to query the exact time a topic is discussed in a podcast does sound valuable.

Do you know of a solution that aims to solve this problem?

Appreciate the feedback. Whether or not a model’s summary represents the underlying text is absolutely something we all have to pay careful attention to as these things improve. One thing we’ve seen work well is systems that always link back to the source so you can see the content that underlied the synthesis. Not a full solution, but important to keep that provanance.

I'll update the UI so the reader can listen to each chapter by themselves and add a disclaimer that these summaries are AI generated and may lack context or be false.

Sorry you feel that way. Have you tried out the demo, it showcases how you can use our tech stack to index across the Joe Rogan podcasts.

For us though it was a nice exercise to show we can support audio transcription and large data files.

Appreciate the comment. Are you referring to the summaries at the bottom of the blog post? Happy to hear more (here or on enias@steamship.com) — if we drew an inaccurate excerpt we should fix it.

Soon!

Steamship is happy to support a company looking to develop this!

We have a database engine layer that can wrap around multiple databases. Today though we're mainly using SQL since it's so fast with the right indexing. Soon though we're planning to support search using embeddings too. We'll probably use an optimised db for that like faiss or ngt.

Me neither. Not planning on spending a year listening to just 1 podcast. :)

Re: quality - Entity extraction is super reliable given proper transcriptions. Summaries are having a hard time though. Some of them give random names to the guests. I saw Elon Musk getting called "Francis" before.

Re: Steamship - We're building a developer SDK for language packages. We're a great solution if you need stateful (you can search using language AI features) or you want an easy interface to tag documents.

We've done text classification before in our ticket tagger. Here's a blog that explains how we did it: https://medium.com/steamship/bootstrapping-classification-wi...

Thanks! Happy you liked it! Theoretically works with any audio/video stream.

I know. And it seems like every influencer out there is starting their own podcast these days. Information overload.

Tv series is a good idea! What insights would you extract from them?

I can already see myself analysing the mood in shark tank pitches. I wonder if you can create a model to analyze all pitches on shark tank and then come up with its own. That would be cool!