Albert Ziegler

@Xbow ...and that's how coincidences work: just a day after the Sonnet / Gemini Alloy post was published, the eval data from #Grok4 comes in: - It beats the Sonnet / Gemini alloy (58% to 55%) - But gets even better when alloyed with Sonnet itself to a mind-blowing 67%

What if two AI models could collaborate without knowing it? Our Head of AI, Albert Ziegler developed "model alloys" - alternating between different LLMs in a single conversation. Sonnet handles some steps, Gemini others, but neither knows about the switch. Result: 55% solve rate vs 40% with single models. xbow.com/blog/alloy-age…

And thanks to my former GitHub team who brought Copilot to life (with OpenAI and Azure): @thewunderalbert, @alexgraveley, @AqeelSiddiqui, @davecheney, @devonrifkin, @eaftandilian, @eleganesh, @johanrosenkilde, Max Schaefer. Let's do it again, but bigger and better!