-
Topics Everyone Is Talking About No411
What Comes After FOSS? • Passphrase-less reboots using kexec under NixOS • AI;DR AI; Didnt Read • Stripe will reportedly acquire OpenRouter for 7B • Qwen 3.8 27B is excellent, but it defaults to overthinking things…
-
Topics Everyone Is Talking About No409
Zig Day Seattle, WA 3 • Why I remain a skeptic • Working with AI Feels More Like Leadership Than Coding • Abdominal fat predicts heart disease risk better than BMI • The First At-Home Test for Infected Ticks Could Improve Lyme Disease Diagnosis…
-
Build your first AI chatbot: from prompt to a working assistant
A useful AI chatbot is not just “a prompt connected to a model.” Even the smallest real application needs a few moving parts: instructions that define behavior, user input, an API call, conversation s
-
Topics Everyone Is Talking About No404
A domain can now say it is for sale, in DNS • The Nixpkgs core team has disbanded • Hardware backdoors in some x86 CPUs • Code was never the hard part is an insult to all programmers • They dont make em like Sublime Text anymore
-
Topics Everyone Is Talking About No384
Forgejo v16.0 Is Now Available • The Human in the Loop Is Running Out of Steam • GrapheneOS Recommended for Domestic Abuse Survivors • Ancient Roman Concrete Reveals the Secret to Millennia of Durability • CD Sales Grew Faster Than Vinyl in Early 2026
-
Topics Everyone Is Talking About No370
Claude Code Sends 33K Tokens Before Reading Your Prompt; OpenCode Sends 7K • Ask HN: Should AI-Generated Articles Be Labeled? • I Love LLMs, but Not the Hype • Irish Data Centers Now Consume 23 of the Nations Electricity • Chromium 148 Makes Math.tanh an OS Fingerprinting Signal…
-
Tokenization pitfalls: why your LLM miscounts characters and money
If you’ve ever asked an LLM to count letters in a word, estimate API cost, or enforce a strict character limit, you’ve probably seen surprising results.
-
How transformer self-attention actually works, with a runnable toy
Transformers power modern large language models, image generators, coding assistants, and multimodal AI systems. The core idea behind them is surprisingly compact: self-attention lets every token deci