First screen, captured .
Looks similar
A Faster Alternative to Jq(micahkepe.com)
358 points by pistolario | 226 comments
Blog post introducing jsongrep, a JSON query tool, explaining its automata-based search engine and benchmarks against jq, jmespath, jsonpath-rust, and jql.
ChatGPT visits the Emacs doctor(xenodium.com)
39 points by xenodium | 1 comments
Claude Code is your customer(calebjohn.xyz)
61 points by mfbx9da4 | 43 comments
TypeChat(microsoft.github.io)
482 points by DanRosenwasser | 145 comments
Microsoft blog post introducing TypeChat, an experimental library that uses TypeScript type definitions to get type-safe structured responses from LLMs.
Related stories
Show HN: Huzzah – a novel approach to coding with AI(danielvaughn.dev)
334 points by danielvaughn | 178 comments
Blog post introducing Huzzah, an experimental editor where you write pseudocode that is synced to real source code by AI on save, with the pseudocode kept as intent.
Qwen3-Next(qwen.ai)
519 points by tosh | 201 comments
Qwen team blog post announcing Qwen3-Next, a model architecture aimed at improving LLM training and inference efficiency.
Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B(phind.com)
737 points by rushingcreek | 258 comments
Phind blog post announcing fine-tuned CodeLlama-34B models that score 67.6% and 69.5% pass@1 on HumanEval, beating GPT-4's reported 67%.
QwQ-32B: Embracing the Power of Reinforcement Learning(qwenlm.github.io)
445 points by nwjsmith | 147 comments
Qwen Team blog post announcing QwQ-32B, a 32B-parameter reasoning model trained with scaled reinforcement learning.
Relicensing with AI-Assisted Rewrite(tuananh.net)
361 points by tuananh | 355 comments
A blog post by Tuan-Anh Tran on using AI-assisted rewrites of code to relicense software away from GPL-family licenses.
Qwen3: Think deeper, act faster(qwenlm.github.io)
808 points by synthwave | 369 comments
Blog post from the Qwen team announcing the Qwen3 family of large language models with hybrid thinking and non-thinking modes.