Stories by knes

Why GPT-5.2 is our model of choice for Augment Code Review

We Added ACP Support to Augment (Now in Zed, Neovim, and Emacs)

Developers are choosing older AI models

The productivity paradox of AI coding assistants

Show HN: Cloud Coding Agents in VSCode

Show HN: Spin up AI coding agents to burn down your backlog

A new Moore's Law for AI agents

New #1 SOTA on Swe-bench is using Claude 3.7 and O1

Show HN: The #1 SWE-Bench AI Coding Assistant for VSCode and Jetbrains

New #1 open-source agent on SWE-Bench Verified by combining Claude 3.7 and O1

New #1 SWE-Bench achieved by combining Claude 3.7 and O1

AugmentQA: A Benchmark to test Code Retrieval on real codebase

Coderag-Bench: Can Retrieval Augment Code Generation?

What we learned building a model that predicts you next code edit

Augment.vim: AI Chat and completion in Vim and Neovim

AI Code Assistant and Chat for Vim

Building a Real-Time Context Engine for Our Code LLM: No More 10-Minute Delays

How We Optimize LLM Inference for AI Coding Assistant

DoorDash tests warning non-tippers that their order could be slow to arrive

1
2
3
4
5
6
7
8
9
10