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

Ask HN: What have you built with LLMs?

news.ycombinator.com

Post reply on HN
Print view View original

91–100 of 349 posts

Re: Ask HN: What have you built with LLMs?

#91

Post by jefc1111 »

bluecoconut wrote: post #25

We've made a lot of data tooling things based on LLMs, and are in the process of rebranding and launching our main product. 1. sketch (in notebook, ai for pandas) https://github.com/approximatelabs/sketch 2. datadm (open source, "chat with data", with support for the open source LLMs ( https://github.com/approximatelabs/datadm ) 3. Our main product: julyp. https://julyp.com/ (currently under very active rebrand and c…

Having a play with datadm. It's really good and intuitive to use - good job! I'm getting errors now, but was having a lot of fun before.

Re: Ask HN: What have you built with LLMs?

#92

Post by eurekin »

ravila4 wrote: post #79
eurekin wrote: post #43

"Widjosumarajzer" = video summarizer It's just a hodgepodge of prototype scripts, but one that I actually used on a few occasions already. Most of the work is manual, but does seem easily run as "fire and forget" with maybe some ways to correct afterwards. First, I'm using the pyannote for speech recognition: it converts audio to text, while being able to discern speakers: SPEAKER_01, _02, etc. The diarization provid…

Very interested in this. I have been contemplating building something similar, but am unaware of any existing services that do this. Haven't played with pyannote, how does it compare to whisper? Also thought it might be useful to be able to OCR screenshots and use the text to inform the summariation and transcription especially for things like code snippets and domain-specifc terms.

I remember whisper v3 large blowing my mind: it was able to properly transcribe some two language monstrosity (przescreenować, which is a english word "to screen a candidate", but conjugated according to standard polish rules). Once I saw that I thought "it's finally time: truly good transcription has finally arrived".

So I view whisper as sota with excellent accuracy.

Now, for the type of transcription I need speaker discerning is much more valuable than accurate to the point translation: so it will be summarized anyway and that tends to gloss over some of errors anyway.

That said, pyannote has also caught me off guard: it correctly annotated lazily spoken "DP8" with non native speaker accent.

It looks really good

Re: Ask HN: What have you built with LLMs?

#94

Post by biosboiii »

Wrote an application to find myself a flat in Berlin, scans some rental websites every minute, uses Google Maps API to calculate the distance to my office, and summarizes the rental description with the GPT-4 API, sends it to me via Telegram.

I have no time to read all that generic "vibrant neighborhood" stuff :D

Re: Ask HN: What have you built with LLMs?

#95

Post by jamifsud »

I'm building https://www.brief.news, an AI powered newsletter that condenses tens of thousands of news articles into a daily briefing of the top stories, we support 30 topics today and are adding the ability to add your own!

Stack is a combination of TypeScript (Next / Node) + Python with a pretty simple deployment setup right now (GHA -> Container -> Cloud Run).

Re: Ask HN: What have you built with LLMs?

#96

Post by jtolster »

I'm currently working on an interface for google calendar @ https://calendarcompanion.io My next feature is integrating the functionality with telegram, it's hard to predict the value of these features in the moment - but I do think this could be an extremely interesting "iPhone" moment for technology. Just like how the iPhone reduced everything to a single button press, we can now squeeze the functionality of some pretty complicated apps into natural language through text - and as the response time of LLM's improves it will become a short conversation for things that used to dazzle new users! Exciting times!

As for the stack, I have Supabase and Typescript on the frontend, python on the backend and k3's as a cluster for my apps (can recommend this if you want to get devops-y on a budget). Next time, I'll just go pure Typescript since python really doesn't add much working this far away from the base models.

Re: Ask HN: What have you built with LLMs?

#97

Post by jtolster »

duckkg5 wrote: post #24

I don't like selling. I wanted a way to practice cold calling in a realistic way. I set up a phone number you can call and talk to an AI that simulates sales calls. I ended up using it for more general purpose things because being able to have a hands-free phone call with an AI turned out to be pretty useful. It's offline now, but here's the code with all the stack and deployment info: https://github.com/kevingduck/C…

Are you finding response time to be an issue? I can imagine some very long pauses might kill the flow of conversation.

Re: Ask HN: What have you built with LLMs?

#98

Post by jtolster »

jamifsud wrote: post #95

I'm building https://www.brief.news , an AI powered newsletter that condenses tens of thousands of news articles into a daily briefing of the top stories, we support 30 topics today and are adding the ability to add your own! Stack is a combination of TypeScript (Next / Node) + Python with a pretty simple deployment setup right now (GHA -> Container -> Cloud Run).

This looks awesome - might I suggest splitting the headlines on the homepage into a punchy title and subtitle? The wordiness of them makes it difficult for me to parse them for the topic quickly

Re: Ask HN: What have you built with LLMs?

#99

Post by elicash »

jtolster wrote: post #97
duckkg5 wrote: post #24

I don't like selling. I wanted a way to practice cold calling in a realistic way. I set up a phone number you can call and talk to an AI that simulates sales calls. I ended up using it for more general purpose things because being able to have a hands-free phone call with an AI turned out to be pretty useful. It's offline now, but here's the code with all the stack and deployment info: https://github.com/kevingduck/C…

Are you finding response time to be an issue? I can imagine some very long pauses might kill the flow of conversation.

To that point, I would love to hear an audio file of it in action since I see from GitHub the phone number is down.

Re: Ask HN: What have you built with LLMs?

#100

Post by benlm »

We built Jumprun. You can use it to research and analyze data sources, and it'll produce beautiful canvases with tables, charts, videos, maps, etc. We're working on automations so you can setup natural language trigger conditions that execute actions.

We built it in Kotlin with Ktor server, htmx and tailwind. It uses a mixture of models, including gpt4-turbo, gpt4-vision and gemini-pro-vision. It's deployed using Kamal on bare metal.

Example canvas that provides a roundup of Apple Vision Pro reviews: https://jumprun.ai/share/canvas/01HNXB2K3GM7KPRP45Y2CVVJSC

Our learn more page with some screenshots to show creating a canvas: https://jumprun.ai/learn-more

It's a free closed beta at the moment to control costs, but let me know if you'd like an invite.

Post reply on HN