Live data from Hacker News

Ask HN: What have you built with LLMs?

news.ycombinator.com

311–320 of 349 posts

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

#311

I wrote a script that takes in my credit card statement line by line and categorized the transactions into a custom set of categories that I cared about as well as generating a human readable description of the transaction.

Was thinking about this the other day too!

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

#312
post #208

https://www.rivadata.com/ I have been hacking together a poor-man's crunchbase that's fueled by GPT. React / Python / Supabase. The most interesting piece thus far has been the success of the self-correcting loops through GPT. At each turn basically feeding the results back to another 3.5 prompt that is only about reviewing quality. I found that with these loops you can get solid results without having to use the mor…

It's funny bc that's exactly how fine tuning is done rn. I find it amusing how we can leverage the same techniques pre and post. Wild wild west

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

#313
post #53
post #42

Earlier quoted context omitted.

So the AI tries to sell to you, or you try to sell to the AI? This sounds very intriguing but I can tell by your README that you're an engineer and not a sales guy - there are no distinct value propositions. But it sounds damn creative as a project.

The AI answers the call and acts as a potential customer. They take on personas to simulate behaviors like difficult or reluctant customers. You then do your pitch, handle objections, etc. At the end you get a transcript that's 'graded' to show you where you could improve your sales approach. And you're right, I'm not a sales guy. This project is for people like me who want a risk-free place to learn the basics of sa…

Love the idea of AI grading the answers, hopefully this can be extended to marking/evaluating/grading subjective manuscripts.

For me there's none is more boring than marking/evaluating/grading manuscripts. I prefer hard labor like gardening or farming than doing that activities although I'm quite good at evaluating stuffs I think.

Can you please elaborate how you do this and based on what metrics/scheme/etc the answers are being evaluated?

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

#314

I am building a no code solution. Use case is simple: Write complete programs/software for the browser from natural language input. https://domsy.io Currently running on my little digital ocean droplet. Stack is javascript/python.

I like it! One of the example is the most straightforward QR code generator I have ever seen too.

https://domsy.io/share/ddf54149-5de9-4f3a-b936-f007a451c0b5

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

#315

I generate and sell books that summarize historical events. I was actually ready to launch last month until I realized I could generate extremely realistic photographs in Midjourney and splice them between paragraphs using a simple python script, so I went back and did another pass. My process involves generating chapters as markdown, using a script to join chapters together, and then finally converting the markdown…

Hey, had a similar idea, would be great to chat - can reach me at my username on google’s mail.

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

#316
I've built an open-source ChatGPT UI designed for team collaboration.

Github Link: https://github.com/joiahq/joia

Benefits vs the original: - Easy to invite entire teams and centralize billing - Talks to any Large Language Model (eg: Llama 2, Mixtral, Gemini) - Collaborative workspace to easily share GPTs within the team, similar to how Notion pages work - Savings of 50%-70% vs ChatGPT's monthly subscription

Tech stack: NextJS, Trpc and Postgres. All wonderful technologies that have helped me develop at the speed of thought.

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

#317

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 whatev…

Great idea! Defense through a trap, where the criminals will be used against themselves, I like it! Do you happen to have an address for your project so I can forward it? I may know people who would be interested in purchasing or supporting it.

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

#318

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

That's hilarious! I always wanted to build something like that and host it on All About Berlin. Unfortunately, ImmobilienScout is working really hard to block bots. How did you get around that?

Fun fact by the way: listings on ImmobilienScout are usually gone after 5 minutes and hundreds of messages.

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

#319

https://www.askaway.bot/ AI concierge for my parents’ vacation rental. Mostly just pulling info from the guest binder, but I’ve also started using some local guides to give better suggestions. Built with NextJs and deployed on Vercel (was really easy and they have a generous free tier).

How well does it work, regarding accuracy?

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

#320

I generate and sell books that summarize historical events. I was actually ready to launch last month until I realized I could generate extremely realistic photographs in Midjourney and splice them between paragraphs using a simple python script, so I went back and did another pass. My process involves generating chapters as markdown, using a script to join chapters together, and then finally converting the markdown…

You really need to tell people that the images are AI-generated. Anyone who remotely cares about history will feel very upset otherwise. Even using real images in the wrong context is a big no-no.

Honestly, for anything non-fiction, I would strongly advise against using fake images.

Post reply on HN