My current set up as of 15 hrs ago: - ghostty as terminal - herdr as organizer - jcode as agent - sitting on anthropic model for planning and glm via baseten for data and code gen work - obsidian for docs and brain dumps overkill? Idk. peaceful and clarifying, absolutely. Fits my style of work

There’s never been a better time to invest in cards. Join the waitlist at for a chance to win an ’86 Fleer Jordan worth ~$10K Every referral = 10 extra entries.

Hey 👋 I maintain @ratatui_rs 🐀 Ratatui powers the new generation of terminal coding agents... and another one just dropped! jcode is an open source Rust agent built for fast, memory-efficient parallel sessions and swarms! 🦀 #rustlang# #ratatui# #opensource# #terminal# #agents# #ai#

Today I'm fixing benchmarks with Jcode bench! Jcode bench is the first open and uncontaminatable benchmark. There are a few problems in the coding benchmarks of today: >Private benchmarks are hard to trust >Public benchmarks are easy to benchmaxx >Benchmark task grading can be too coarse or wrong >Benchmarks give little signal to distinguish between the frontier and mid models >Benchmarks are easy to saturate >Benchmarks don't represent the real world coding work. Jcode bench fixes these problems. The layout is like this: Given one reference implementation, optimize it as much as you can. This approach produces a high signal, continuous score over time. Because there is not a known optimal implementation for these tasks, there is no solution answer to train on. If frontier model task transcripts have been trained on, then generate new tasks to spec, and rerun. Transcripts and tasks are able to be audited to do it's open nature. When it's believed that a set of SOTA transcripts have been trained, simply generate a new set of tasks to spec and rerun. spec: results: Individual tasks:

@TryTrustAI is building the fastest, cheapest lightweight inference by optimizing KV cache at @ycombinator. Our group of MIT grads and olympiad medalists from @GoogleDeepMind, @JaneStreetGroup, and NeurIPS/ICML publishers are setting a new standard for cost and latency efficiency.

I run 20 coding agents in parallel as my everyday workflow. Today, I’m launching Jcode. It’s an open-source agent 20x more memory-efficient than Claude Code, so you can run 20x more agents at once. Try it today: