Pgbot: A 5.9 MB read-only Postgres tool for humans and agents(pgbot.dev)

43 points by sashash 2 months ago | 10 comments

Demographics of Hacker News(toolhub.tech)

34 points by sine_break 3 years ago | 35 comments

A sharded DuckDB on 63 nodes runs 1T row aggregation challenge in 5 sec(gizmodata.com)

196 points by tanelpoder 1 year ago | 121 comments

The Case Against PGVector(alex-jacobs.com)

353 points by tacoooooooo 11 months ago | 132 comments

Blog post by Alex Jacobs arguing about the operational problems of running pgvector for vector search in production that typical posts omit.

Web scraping with GPT-4o: powerful but expensive(blancas.io)

327 points by edublancas 2 years ago | 155 comments

Blog post by Eduardo Blancas describing how to use GPT-4o to scrape tables from websites, with a demo app and source code, and noting its cost.

Software engineer titles have almost lost all their meaning(trevorlasn.com)

98 points by doppp 2 years ago | 93 comments

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge(news.mit.edu)

336 points by CharlesW 2 years ago | 121 comments

MIT News article on research showing LLMs often retrieve stored facts via simple linear functions, and a technique to probe what a model knows about subjects.

AI tools are spotting errors in research papers(nature.com)

555 points by kgwgk 1 year ago | 200 comments

Nature news article on a growing movement using AI and large language models to detect errors in research papers, sparked by a flawed black plastic utensils study.

AI is just unauthorised plagiarism at a bigger scale(axelk.ee)

665 points by speckx 5 months ago | 542 comments

A personal blog post arguing that AI companies train on authors' work without consent or compensation, amounting to plagiarism at scale.

Auto-grading decade-old Hacker News discussions with hindsight(karpathy.bearblog.dev)

637 points by __rito__ 10 months ago | 261 comments

Andrej Karpathy blog post about using LLMs to grade decade-old Hacker News discussions and commenters' predictions with hindsight, presented as an "HN Time Capsule" site.

Why I'm still bearish on LLMs after Navier-Stokes(dank.systems)

426 points by jaykru 1 month ago | 552 comments

Personal blog essay by Jay Kruer arguing LLMs remain overhyped despite headline results like Navier-Stokes, citing poor generalization, reward hacking, and specification costs.

AI Made Writing Code Easier. It Made Being an Engineer Harder(ivanturkovic.com)

343 points by saikatsg 7 months ago | 242 comments

Blog post by Ivan Turkovic arguing that AI tools make producing code easier while making the broader job of being a software engineer harder.