Hacker News with Generative AI: LLMs

A thought on JavaScript "proof of work" anti-scraper systems (utoronto.ca)
One of the things that people are increasingly using these days to deal with the issue of aggressive LLM and other web scrapers is JavaScript based "proof of work" systems, where your web server requires visiting clients to run some JavaScript to solve a challenge; one such system (increasingly widely used) is Xe Iaso's Anubis.

Web Scraping, JavaScript, Security, Artificial Intelligence, LLMs

194 points by zdw 33 days ago | 207 comments

How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph (memgraph.com)
Ever wondered how NASA identifies its top experts, forms high-performing teams, and plans for the skills of tomorrow? The answer lies in their People Graph!

NASA, Graph Databases, LLMs, Knowledge Graphs, Human Resources

107 points by lexmo67 61 days ago | 53 comments

Show HN: I built a tool that generates quizzes from documents using LLMs (ycombinator.com)
Hey everyone! I recently built this little side project that takes any document you upload and turns it into practice quizzes using LLMs to generate the questions: https://www.cuiz-ai.com

LLMs, Generative AI, Education, Tools

10 points by nelson687 90 days ago | 5 comments

The Modern Document Processing Stack (github.com/marcelmarais)
This is a production-ready document conversion and processing engine (and primarily a wrapper of other tools). It uses open-source libraries to convert common file formats (PDF, DOCX, etc.) and web content to Markdown—a format that is friendly for LLMs and embedding models.

Document Processing, Open Source, LLMs, Markdown, File Conversion

9 points by marcelmarais 145 days ago | 4 comments

Show HN: Bring-your-own-key browser extension for summarizing HN posts with LLMs (github.com/ivanyu)
A bring-your-own-key browser extension for summarizing Hacker News articles with OpenAI and Anthropic LLMs.

Browser Extensions, LLMs, Hacker News, OpenAI, Anthropic

74 points by ivanyu 197 days ago | 29 comments

IBM's new SWE agents for developers (research.ibm.com)
IBM SWE-Agent 1.0 from IBM Research is the first set of software engineering (SWE) agents of its kind powered by open LLMs that can autonomously resolve GitHub issues efficiently.

Software Engineering, Artificial Intelligence, GitHub, Open Source, LLMs

77 points by sandwichsphinx 248 days ago | 72 comments

LLM Agent Arena from Gorilla X Lmsys Chatbot Arena (agent-arena.com)

LLMs, Chatbots, AI

12 points by shishirpatil 267 days ago | 0 comments

Show HN: LLM-aided OCR – Correcting Tesseract OCR errors with LLMs (github.com/Dicklesworthstone)

OCR, LLMs, Generative AI, Software, Open Source

479 points by eigenvalue 322 days ago | 172 comments

Show HN: Ell – A command-line interface for LLMs written in Bash (github.com/simonmysun)

LLMs, Open Source, Bash

214 points by simonmysun 329 days ago | 84 comments

Our guidance on using LLMs (for technical writing) (ritza.co)