An open source retrieval augmented generation (RAG) framework:
Ask HN: What have you built with LLMs?
201–210 of 349 posts
Re: Ask HN: What have you built with LLMs?
#202LLM agents to forecast geopolitical and economic events. - Site: https://emergingtrajectories.com/ - GitHub repo: https://github.com/wgryc/emerging-trajectories I've helped a number of companies build various sorts of LLM-powered apps (chatbots mainly) and found it interesting but not incredibly inspiring. The above is my attempt to build something no one else is working on. It's been a lot of fun. Not sure if it'll…
Very interesting, have you attempted to backtest to see if the LLM forecasts are accurate?
Re: Ask HN: What have you built with LLMs?
#203LLM agents to forecast geopolitical and economic events. - Site: https://emergingtrajectories.com/ - GitHub repo: https://github.com/wgryc/emerging-trajectories I've helped a number of companies build various sorts of LLM-powered apps (chatbots mainly) and found it interesting but not incredibly inspiring. The above is my attempt to build something no one else is working on. It's been a lot of fun. Not sure if it'll…
Fascinating. I've done this on a tiny, micro scale -- giving the GPT scenarios (eg, conversations, situations) and asking how it would play out. In early 2023 it seemed to work really well, now that they've nerfed it so much, it's a bit too generic and proper.
Re: Ask HN: What have you built with LLMs?
#204LLM agents to forecast geopolitical and economic events. - Site: https://emergingtrajectories.com/ - GitHub repo: https://github.com/wgryc/emerging-trajectories I've helped a number of companies build various sorts of LLM-powered apps (chatbots mainly) and found it interesting but not incredibly inspiring. The above is my attempt to build something no one else is working on. It's been a lot of fun. Not sure if it'll…
Very interesting, have you attempted to backtest to see if the LLM forecasts are accurate?
Thanks for asking! Not yet as I’ve been focusing on building agents that can properly and regularly log predictions.
Ideally, I’d like the agents to then participate in prediction markets or “superforecasting” groups to use actual human predictions as baselines.
Re: Ask HN: What have you built with LLMs?
#205LLM agents to forecast geopolitical and economic events. - Site: https://emergingtrajectories.com/ - GitHub repo: https://github.com/wgryc/emerging-trajectories I've helped a number of companies build various sorts of LLM-powered apps (chatbots mainly) and found it interesting but not incredibly inspiring. The above is my attempt to build something no one else is working on. It's been a lot of fun. Not sure if it'll…
Fascinating. I've done this on a tiny, micro scale -- giving the GPT scenarios (eg, conversations, situations) and asking how it would play out. In early 2023 it seemed to work really well, now that they've nerfed it so much, it's a bit too generic and proper.
Have you tried GPT-4 with the update from the past few days? (When Sam mentioned it should be less lazy.) I notice it’s gotten much better and more willing to make forecasts since then.
Re: Ask HN: What have you built with LLMs?
#206I built a simple RAG chatbot, and my "stack" is plain openai python client at this point.
Re: Ask HN: What have you built with LLMs?
#207Earlier quoted context omitted.
Fascinating. I've done this on a tiny, micro scale -- giving the GPT scenarios (eg, conversations, situations) and asking how it would play out. In early 2023 it seemed to work really well, now that they've nerfed it so much, it's a bit too generic and proper.
Have you tried GPT-4 with the update from the past few days? (When Sam mentioned it should be less lazy.) I notice it’s gotten much better and more willing to make forecasts since then.
No but I'll check it out. Thanks!
Re: Ask HN: What have you built with LLMs?
#208https://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 more expensive GPT4 API.
(Also loving all the projects in this thread)
Re: Ask HN: What have you built with LLMs?
#209A BERT-based summarization system for financial earnings calls. It can take a 60-minute transcripts of such meetings can compress the contents down into 5 bullet points. https://link.springer.com/chapter/10.1007/978-3-031-28238-6_... Financial earnings calls are important events in investment managements: CEOs and CFOs present the results of the recent quarter, and a few invited analysts ask them questions at the end…
Oh funny, i've been working on a similar project, analyzing earning call transcripts using LLM's. My first attempt was with BERTopic. The results were awful. My second attempt was with a finetuned 7B version of Mistral, with heavy prompt engineering, the results were actually super good in my opinion... plus it runs on a single 3090.
Re: Ask HN: What have you built with LLMs?
#210I am working on a part search engine for company maintenance teams. We built a search engine that searches parts in real time across a dozen or so vendors (Amazon, eBay, McMaster, etc). We then leverage Chat GPT to extract data from product titles. Part number is one of the key elements we extract. Since part numbers vary greatly across manufacturers, it's difficult to throw something like a regex at it. It has done a really good job so far for data extraction.