Hacker News with Generative AI

Everything I own, owned (schlarp.com)
I were 17, I'd learn how to build LLMs from scratch (twitter.com)
FDA clears blood test to aid evaluation for Alzheimer's disease (medicine.washu.edu)
Anthropic's best AI model struggles to attract users as cheaper tools thrive (ft.com)
OCR It – pull text out of un-copyable documents for your LLM (github.com/thiagotigaz)
How I find problems to solve as a staff engineer (lalitm.com)
Executable Is a SQLite Database (fzakaria.com)
Andreessen Horowitz is investing billions into a bleak future (modelrepublic.org)
Woman stranded in Spain after UK's eVisa system mistakes her for twin sister (theguardian.com)
The Future Belongs to the Weird (georgestrakhov.com)
I built a low-latency AI companion that plays Skyrim with me (pantel.is)
New EU-wide product repair rules come into force (rte.ie)
Google Workspace thinks my domain is an email provider (2025) (elis.cc)
My agent.md to improve LLM-assisted code quality (fabiensanglard.net)
What Is a Harness? (earendil.com)
Over 5,200 Ebola cases recorded in Congo (afro.who.int)
How Complex Systems Fail (1998) (complexsystems.fail)
Malware infects Android-based automotive head unit firmware (securelist.com)
AI Chip Architectures (jepeake.com)
Fast drilldown dashboards from a single Parquet file (hamiltonulmer.com)
Fable and the end of the free lunch (dbreunig.com)
My favorite nonfiction books about cults, scams, and schemes (bookdna.com)
Migrating a Synology NAS to a UniFi UNAS Pro 8 with Robocopy, SMB Multichannel (hanselman.com)
Explain it to me like I'm ten (timharford.com)
Why Sal Khan't: On Learning by Making but Teaching by Telling (punyamishra.com)
Elevated Errors for Multiple Models (claude.com)
Why is Anthropic's public writing style so unlike Claude's? (cmart.blog)
A website for debloated open source alternatives (debloat.dev)
Implementation of GPT-2 in pure CMake (github.com/AlpinDale)
Anthropic Claude and API service outages (claude.com)