I've been experimenting with @openclaw for the past two months. Some moments have been genuinely great, and some have been deeply frustrating, especially around deterministic tool use for custom CLIs and calls that were never in any model's training data. I flipped around hooking up Claw to the frontier models, while keeping an eye on the $$$ meter. So after a while, I asked Claude Code to analyze my Claw chat logs (ie. arguments) and distill a benchmark dataset based on exactly where models had failed me (!) The result was a set of bespoke requests, 28 prompts across two sets: assistant-specific tasks (correct CLI syntax, memory hygiene, calendar edge cases, following instructions without mid-run re-planning) and general reasoning. This becomes a personal benchmark dataset I can use to evaluate new models. I then ran every model I’m considering and ranked them by what actually matters for a daily driver: latency (70%), benchmark accuracy (25%), and cost per call (5%). What I really want (!) set a default model, let it run, not worry about how much the tokens are costing, not be frustrated that my Claw is just … dumb 😂 because of the model choice. Check out my Personal Claw Capability Leaderboard! The standout models at the top were fast and accurate, surprisingly Ling 2.6, Gemma-4 26B, and GPT-5.4 all scored within a point of each other while staying under 2.5 seconds. Bigger, slower models with higher benchmark scores ranked lower because wall-clock responsiveness matters more than raw capability when you're waiting on your Claw to get back to you on Telegram. Really impressed how well Ling-2.6-1t and Gemma-4-26B ranked! GPT-5.4 and GPT-5.4-nano also held up, without breaking the piggy bank 🐽💸 Encourage folks to generate your personal capability benchmark- and hold the models to account!

Since @tomwarren screenshotted my LinkedIn post and some folks are conspiracy theorying it (wtf). Posting here my farewell love letter to Microsoft. Today was my last day on campus, and after spending 13 years in this place, choosing to leave this company and these amazing people was the hardest decision of my life🥹❤️. And at the same time, I always said I want to go on many adventures in my life… moving from Australia to Canada, to Italy, to SF, to London… then Redmond with Microsoft. Now on to a new journey— After more than a decade at Microsoft, I’ve decided to step into the next phase of my career, which will take me on a new adventure beyond Microsoft. Reflecting back, I still remember stepping through the doors at 30 Great Pulteney Street on March 27, 2013, into a newly formed Xbox game studio in London. I felt at once excitement, trepidation, and optimism. As I step into this next chapter, I find many of those same emotions returning as I look ahead. Thank you to everyone who has been part of my journey at Microsoft. To the many colleagues, collaborators, and supporters who opened your office doors, and who spent time sharing your thoughts and encouragement - I am deeply grateful. At Microsoft, I felt I had truly found my people: a place where I could belong. I hope I carry forward some small piece of the culture we built together: one of curiosity, acceptance, and inclusion. Thank you all for walking this journey with me, from my early days in Xbox Game Studios, to Microsoft Research, to serving as Gaming Chief of Staff, and more recently working together on this AI revolution. I’ve loved the adventure. My next step will be at Netflix, where I’ll be joining the team to help empower their journey in gaming. I’ll also continue pursuing my passion for advancing AI for social impact through my nonprofit, Thriven Foundation (lnkd.in/gyqmp3UE) Cheers to all of you and to the journeys ahead!