Sonnet 4.5
We've gotten used to vendors changing multiple things at once with their flagship releases, but Anthropic is playing a more conservative game.
Jonathan Ellis
Cheap, Fast, or Smart? Evaluating Grok Code Fast 1
The pitch for the awkwardly-but-accurately named grok-code-fast-1 is: it's pretty
Introducing the Brokk Power Ranking
The Brokk Power Ranking is a new open-source coding benchmark, featuring 93 tasks from large, real-world codebases.
A first look at GPT-OSS-120B’s coding ability
As part of the Brokk Power Ranking of coding models coming next
Context Engineering with Brokk
“Everything should be made as simple as possible, but no simpler.”
Context
LLMs and Artists
Today the craft of software is going through its own studio-like renaissance. That clicked for me when Simon Willison recently observed that when you take an experienced engineer and have him write a quick and dirty project via LLM, what you get out of it is … actually good code.
Brokk: AI for Large (Java) Codebases
There are two reasons that AI makes mistakes writing code:
1. The
Brokk: The Run Down
Check out this video to learn more about Brokk, a revolutionary AI
Brokk: Under the Hood
Brokk is an open source IDE (github here) focused on empowering humans
The Best LLM for Code
I’ve been using Brokk to build Brokk for several months, so I have strong opinions about the best models to use for code.