Claude 4.5 Haiku Codes Like It’s Late for a meeting with God
Claude 4.5 Haiku just landed and it is smoking hot.
In
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.
Brokk’s Modernization Update: A Fresh UI, Faster Performance, and MCP Support
Brokk has just released one of its most significant updates so far, rethinking not only how the product looks but also how developers use it day to day.
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.
Brokk Vs. Cursor: Massive Refactors in Minutes
We put Brokk head-to-head with Cursor to see which tool could deliver the fastest results.
GPT-OSS Underperforms in Independent Testing
We put OpenAI's newly released GPT-OSS model through our own independent benchmark, the Brokk Power Ranking, to see how it really performs on coding tasks.
A first look at GPT-OSS-120B’s coding ability
As part of the Brokk Power Ranking of coding models coming next
Massive Refactors in Minutes
We set out to compare the performance of our AI-assisted development tool, Brokk, against Cursor, a well-known AI coding assistant.
Context Engineering with Brokk
“Everything should be made as simple as possible, but no simpler.”
Context
BlitzForge: Refactor at Scale
Say hello to BlitzForge, the powerful new tool in Brokk that helps you plan and apply large-scale code changes with confidence and speed.
Accelerating Development with Brokk BlitzForge
Modern codebases often span hundreds, if not thousands, of files. Even the