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

281–290 of 349 posts

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

#281

Post by guidsen »

I'm building https://www.getmosaic.io that helps GTM teams enrich lead data and power personalization at scale, by integrating 30+ data providers and web scraping.

I've built this by using AI as the foundation for everything. I am using LLMs to classify information and extract structured data points for any webpage, or RAG for finding data.

Tech stack: - Mistral 8x7b and Perplexity API for data processing and GPT-4 input - GPT-4 for content output - pgvector in Supabase - LangChain for the pipeline and RAG stuff

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

#282

Post by whiskeykilo »

bomewish wrote: post #229
instagary wrote: post #161

We're building a GPT for managing your finances. https://candle.fi/gpt Our backend stack: - AWS - SST - TypeScript Our clients: - Next (web) - Vanilla React Native (mobile) OpenAI's App Store announcement is what got us interested in building w/ LLMs.

Why not show names and faces of the founders? Explain the backstory. Using your service requires users put absolutely enormous trust in you. But there is currently nothing on the site to engender that trust. I would work on that as a priority.

Even more ominous that it's free

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

#283

Post by hn_7 »

fullstackchris wrote: post #153

I'm building a way to automate creation of software video lessons and courses, putting it all under the name 'CodeVideo'. One tool leverages OpenAI's whisper, as well as GPT3.5 or GPT4 for help with generating the steps that ultimately produce the video (this part is not yet in the repo; everything is a work in progress). The tool is here: https://github.com/codevideo/codevideo-ai My goal is to definitely NOT generat…

This is super interesting. From what I gathered, generating a video autonomously given the content or instructions is sort of difficult. Curious to hear if you (or others) have any leads on how you can build this? (I'm assuming you intend to generate an instructional course video given the content) If this works well, could be used for teaching students via auto-generated video.

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

#284

Post by hn_7 »

jtap wrote: post #122

I built out a few utilities as experiments. One app linked to Salesforce to query/analyze sales data. Another that reads our help documentation and gives instructions via chat. The last app, the only one that was deployed anywhere, is https://catchingkillers.com This app is a simple murder mystery game where the witnesses and the killer are ChatGPT bots. The first two stories are complete and active, the third is not…

Is the salesforce data in a structured (SQL-like) format? Or uploaded documents?

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

#285

Post by isenhaard »

geor9e wrote: post #185

My "stack" is just Apple Shortcuts making HTTP POST API calls to OpenAI, which does stuff in MacOS via BetterTouchTool. I trigger each by hotkey or typing a few letter into Spotlight (with Alfred). One transcribes and summarizes whatever youtube URL is highlighted. One does grammar and style correction of whatever is highlighted (and replaces it). One simply replaces the Dictate key with OpenAI Whisper but otherwise…

I really love that, super good ideas. I also generally love to create workflow optimizations. Will probably create some of your stuff for myself (I especially like the dictation replacement, could be super useful to me).

Wondering: How big is you monthly OpenAI bill when using all these tools? Only a few $$$, or is it higher?

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

#286

Post by isenhaard »

jonnycoder wrote: post #279
wayfareryouth wrote: post #216

Earlier quoted context omitted.

I’m sorry it’s been tough. The job market for seniors and leads is still quite strong in Australia if you can move here

Thanks. I'm starting to realize that part of the problem is job search and matching. I was contacted by a company recruiter for a small healthcare SaaS in California and had 3 interviews recently. When I looked up the job, only 7 people had applied in 2 weeks on LinkedIn. They are a very real company with very real people, but their job post is not getting seen (it's not a promoted post). My next AI project will be t…

Just played with your app, I think is super cool! I especially liked the way that you can just click the next question within an answer, makes it super convenient and fun to use.

I'm currently also looking for a dev job. So you have 15 years of experience, live in California and struggle to find something? That sounds a bit demotivating to me lol, because I'm kinda half of all of that or a bit less.

I also like your LinkedIn analysis idea, should try that maybe, too.

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

#287

Post by cmgriffing »

coderKen wrote: post #221
cmgriffing wrote: post #101

I just built a tool that uses Whisper.cpp compiled to WASM in conjunction with SQLite WASM for a fully client-side book writing tool. Basically, I want to write a book without having to type out the whole thing. I got the dictation idea from an episode of Columbo. It is very much a work in progress and a proof of concept for another writing tool I want to make. https://orderly.cmgriffing.com/ https://github.com/cmgri…

This is awesome! What is the performance like? particularly around WASM compiled Whisper.

Thanks! It really depends on your machine.

My mac mini is heavily constrained due to only having 2 proper cores and not much RAM. So the smallest models run best. The quantized tiny runs better than the regular tiny simply due to memory pressure.

So, in my testing on my mac mini it tends to take about 30% more time to process than the audio clip that was recorded. I added a specific warning that lets the user know to reduce their thread count if the processing time takes longer than a specific threshold.

Some of my stream viewers report it being pretty fast though. (much faster than what they see on my mac mini).

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

#288

Post by elimc184 »

I used an LLM connected to a messaging service to defeat romance scammers. I was able to get these romance scammers to speak to my program for hours without knowing they were talking to a machine. Essentially, it's a DDOS for scammers. The scammers can only talk to a few dozen victims at a time, while the "people" in my programs can be spun up by the millions. It will essentially eliminate messaging scams from whatever messaging platform it's on.

I believe a large company like Meta, or any of the other companies with messaging platforms, would find this valuable. Especially because they will be fined by the UK for fraud that takes place on their messaging services.

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

#289

Post by isenhaard »

jonnycoder wrote: post #279
wayfareryouth wrote: post #216

Earlier quoted context omitted.

I’m sorry it’s been tough. The job market for seniors and leads is still quite strong in Australia if you can move here

Thanks. I'm starting to realize that part of the problem is job search and matching. I was contacted by a company recruiter for a small healthcare SaaS in California and had 3 interviews recently. When I looked up the job, only 7 people had applied in 2 weeks on LinkedIn. They are a very real company with very real people, but their job post is not getting seen (it's not a promoted post). My next AI project will be t…

... btw. are you sure that only 7 people applied for that job? Because there are a lot of job announcements on LinkedIn which just won't show the number of applicants correctly in case there's an application link outside of LinkedIn for applying, meaning the application doesn't take place within LinkedIn. In that case, you'll get the question by LinkedIn if you have applied for the job, which most people just won't click. I'm seeing this all the time.

But still good point that there might be promoted jobs and non-promoted ones, maybe it's worth creating an own job scraper.

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

#290

Post by jamifsud »

riku_iki wrote: post #147
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).

How much money you need to spend per day on OpenAI api?

A lot! We’re actively reducing that though by training our own specialized models. We’re seeing equal or better performance with curated datasets at > 10x cost reduction.
Post reply on HN