Hacker News with Generative AI

Bijou64: A variable-length integer encoding (inkandswitch.com)
I Am Retiring from Tech to Live Offline (openpath.quest)
Tulip mania: when a single flower was worth more than a house (2025) (dutchreview.com)
Expertise in the Age of AI (moderndescartes.com)
High Density Living, 2000 Years Ago: Inside the Roman Apartment Building (commonedge.org)
The UK Government's Low Value Purchase System Is a Waste of Time (shkspr.mobi)
Blue Origin's New Glenn blows up during static fire test (twitter.com)
Headway Therapy Patients Forced to Scan Their Faces to Keep Getting Care (404media.co)
Real-time LLM Inference on Standard GPUs: 3k tokens/s per request (kog.ai)
Claude Code – Everything You Can Configure That the Docs Don't Tell You (buildingbetter.tech)
It's hard to justify buying a Framework 12 (jeffgeerling.com)
Orchestrating AI code review at scale (cloudflare.com)
Claude Opus 4.8 (anthropic.com)
Bricks and Minifigs Stole a Man's $200k Lego Collection (mybricklog.com)
GTA 6 Developers Unionize (rockstarintel.com)
The Secret Garden of Rock-Paper-Scissors (theshamblog.com)
Danish Pension Blacklists SpaceX over 'Catastrophic Governance' (bloomberg.com)
An Obsessive Focus on UX: Pilot's Pressure-Regulating Kire-Na Highlighter (core77.com)
Let's compile Quake like it's 1997 (fabiensanglard.net)
Is AI causing a repeat of Front end's Lost Decade? (mastrojs.github.io)
Wterm – Terminal Emulator for the Web (wterm.dev)
Even (very) noisy LLM evaluators are useful for improving AI agents (tensorzero.com)
Local Git Remotes (cblgh.org)
Volkswagen blocks Home Assistant by requiring client assertion (github.com/robinostlund)
Social media bans for teenagers lack evidence and pose risks, scientists say (frontiersin.org)
Italians and Dutch share the same gestural instinct for teaching (mpi.nl)
Ten Basic Clouds (noaa.gov)
Show HN: Context-aware Japanese furigana using Sudachi and ModernBERT (ezfurigana.com)
We should be more tired than the model (vickiboykis.com)