AI Code Review Without Code Review Is Cooked
Future of Dev

AI Code Review Without Code Review Is Cooked

The 'test-only, zero code review' workflow sounds fire until you realise you're just trading one hell for another. LLMs aren't compilers, context windows hit physical limits, and someone still has to review all those AI-generated test cases. Spoiler: that someone is you.

· 5 min read
I Made a Portrait Talk Using One Audio File and Zero Cloud Servers
Open Source

I Made a Portrait Talk Using One Audio File and Zero Cloud Servers

InfiniteTalk is an open-source framework that generates unlimited-length talking videos from a single portrait and audio file. No cloud processing. No usage logs. Just your GPU and some electricity. Here's what happened when I tried to replace a $1,100 video production quote with three days of local compute.

· 4 min read
Building an LLM from scratch: how tokens become vectors (with actual code)
Future of Dev

Building an LLM from scratch: how tokens become vectors (with actual code)

Computers speak voltage, humans speak words. This creates a problem. The naive fix is a dictionary (Apple = 1, Ball = 2), but it loses meaning. The real solution? Embeddings that turn text into GPS coordinates where 'king' lives next to 'queen' and far from 'banana'. Here's how tokenization and BPE actually work, with Python you can run today.

· 3 min read
Vim 9.2 Ships XDG Support and Enums (Finally)
Languages

Vim 9.2 Ships XDG Support and Enums (Finally)

After two years and 2,000+ patches, Vim 9.2 dropped on Valentine's Day with the features devs actually wanted: XDG Base Directory support, native enums, and generics. The release notes? Possibly AI-generated. The discourse? Absolutely unhinged.

· 3 min read