#lines

Show HN: DeepSeek V3 in ~200 lines of pure Jax

DeepSeek V3 (MLA, DeepSeekMoE, aux-loss-free balancing, MTP) in 190 lines of pure JAX, trained on a MacBook Air. Write-up: vaibhaav.in/writing/deepseek-v3-jax - Vaibhaav-Tiwari/deepseek-v3-jax

Show HN · EN

Show HN: Bright Lines – a fail-closed guard hook for Claude Code

Supervised, fail-closed safety setup for Claude Code - LeriderTechnologies/bright-lines

Show HN · EN

Gods of straight lines on graphs strike Starburst. I am shocked and puzzled.

LLM Intelligence, measured by Starburst, has been basically linear over time since that start of the reasoning era. By Chapin Lenthall-Cleary and Cole Gaboriault In summer 2024, my friend Cole and I started a hobby research program into perceptions of (human) intelligence. We started by creating a bespoke 1-5 intelligence scale [1] and rating people we knew. Our plan was to then make a bunch of tests, give them to the people we rated, and see which tests, if any, correlated with our ratings. One of those tests was Starburst. We’ve talked about it before ; in short, it’s a puzzle game where one

LessWrong · EN

The brief history of lsp_lines.nvim

Back in 2022, LSP implementations could find errors and other diagnostics in code and send them into the editor, but editors lacked good interfaces to actually present this. The best at the time was a panel with a list of errors (not unlike what Eclipse and other IDEs would do a decade earlier). I wanted to see errors in context instead. I found inspiration in how Rust renders compilation errors and warnings into the terminal: rendering a portion of surrounding code, and an ASCII arrow pointing to the relevant portion of code. With the idea, I implemented lsp_lines.nvim , a plug-in that render

Hugo's weblog on WhyNotHugo (雨果) · EN