Researcher, Entrepreneur, Lover of the North
London & Stockholm
Joined May 2012
- Tweets13
- Following156
- Followers92
- Likes22
Maestro (our agent) is making the most of Sonnet 4.6 already - showing great results!
We’ve been testing Sonnet 4.6 and it has been potent in our agent, Maestro. Our primary eval is to implement a long list of features across a diverse set of use cases, iteratively across codebases, building on prior work. The result: it completed features faster, cheaper, and with a higher benchmark pass rate.
This is a historic moment for us.
Our software engineering agent, Maestro, generated solutions for all 12 ICPC World Finals problems — one of the hardest team programming competitions on Earth!
We're opening its solutions for the community to validate. Go break them.
Anthropic just made *the* LLM release we have been waiting for - two massive context Claude Sonnet models, handling up to 1M input tokens. These are the models that we used with our Maestro system @iGent_AI to build large, complex software, like a Redis-compatible database written in Rust, written entirely by AI nitter.gq/MSzummer/status/195385…
Our agentic software engineering system, Maestro, can build large, complex software: it just finished building a Redis database from first principles in Rust, improving on its safety and performance!
Martin Szummer retweeted
You can also find out the full details on Sonnet 4.0 VibeCodeBench performance at igent.ai/sonnet4eval.pdf
Martin Szummer retweeted
We've integrated Claude Sonnet 4 into Maestro, and the results are transformative. As our evaluations show, it maintains higher code quality even as project complexity grows. Combined with its new extended thinking capabilities, Maestro delivers an unmatched AI engineering experience. Signup at igent.ai/
Martin Szummer retweeted
@Anthropic reports Claude 4 models are 65% less likely to use shortcuts on agentic tasks. Our evaluations confirm this—Claude Sonnet 4 consistently understates feature completeness rather than overstate success. This translates to more reliable AI assistance through Maestro.
Martin Szummer retweeted
Our VibeCodeBench evaluations affirm what @Anthropic just announced: Claude Sonnet 4 excels at autonomous multi-feature development. We've seen codebase navigation errors drop from 20% to near zero and strategic refactoring that saves ~500k tokens on multi stage, complex tasks. Proud to power Maestro with this breakthrough.
Introducing the next generation: Claude Opus 4 and Claude Sonnet 4.
Claude Opus 4 is our most powerful model yet, and the world’s best coding model.
Claude Sonnet 4 is a significant upgrade from its predecessor, delivering superior coding and reasoning.
ALT A benchmarking table titled Claude 4 benchmarks comparing performance metrics across various capabilities including coding, reasoning, tool use, multilingual Q&A, visual reasoning, and mathematics.
3 of us are planning a hike/cycle trip in Scotland following the #ICML2012 workshops (July 2-3-4); Anyone else wants to join? Bring boots!