I got tired of public data being silo'd or difficult to search or aggregate. LLM's could only handle so much and slowly. So I built a free site and loaded lots in. Know of any other data to pour in, LMK. Comments URL: https://news.ycombinator.com/item?id=50173235 Points: 1 # Comments: 0
Article URL: https://github.com/harsheetamorey/mediaindex Comments URL: https://news.ycombinator.com/item?id=50172995 Points: 1 # Comments: 0
Trying to pull up information for certain peptides on TikTok is now returning a "no results found" page when searching for terms like semaglutide, BPC-157, retratutide, and others. That hasn't entirely erased visibility on TikTok for peptides, which are combinations of amino acids that include substances like insulin and GLP-1. The problem is peptides also […]
I built a claude mod that searches every session (across harnesses) on each prompt. On every prompt, it runs a series of decision models to pick the right sessions + messages and adds anything relevant to the context. Requires no indexing or setup and works out of the box Demo: https://youtu.be/o5vEf8tgus4 Comments URL: https://news.ycombinator.com/item?id=50169411 Points: 2 # Comments: 0
I got into homelabbing a year ago and have been deploying OSS and making some of my own to address some pain points in my everyday life. One particular area I thought I could improve was keeping in touch with people. Well that first required having a centralized place to see all my contacts. I have some friends on my Google contacts, other relationships on LinkedIn and even some in Facebook. A secondary need is something that's been blowing up recently with people search. LLMs + Search are surprisingly good at aggregating relevant data and parsing through for relevant information. And finally…