
Staff Eng @Shopify (building @Shop) Former @reactnative core maintainer Ex-@Microsoft @sovtechagency open source • tech • mental health • agentic
London, Europe, Earth 🌍
Joined March 2009
- Tweets26.5K
- Following1.3K
- Followers8.6K
- Likes49.8K
One of the nicest things, my mom was a store owner and sadly didn’t have shopify during covid. Now seeing folks get to success is beautiful
She just received her first @Shopify order and started crying.
When I worked at Shopify I saw that reaction and what the first order meant for entrepreneurs through countless - incredible - videos.
But this was the first time in person and in the moment.
Beautiful.
i know i'm super tunnel visioned but in the last week i've noticed so many more apps on my iPhone update to use native/glass toolbars and tabbar... I KNOW WHAT YOU ARE DOING DEVS 😂
sending hugs to y'all, the iPhone Duo support wave is real
✨Shop is gonna look so fine on it✨
this is amazing
Feeling cheesy? Built this iPhone Duo concept this morning with Opus 5.5 via @splinetool MCP. Designed by hand in Figma/Ps whilst eating a cheese toastie and drinking waay too much coffee.
Genuinely the first time I've utilised 'Bevel & Emboss' since 2006.
Why did I build it? I have no idea. 🧀 🖤
Lorenzo 'kelset' Sciandra retweeted
Oh my god, Firebase’s SDK started to crash ALL iOS apps that were using it, for ALL sessions, just like that, no way for any of these apps to do anything…
How amateur is all of this from any SDK, but especially one from a company with as high of an engineering bar like Google…
github.com/firebase/firebase…
incase anyone has been wondering why their iOS apps are intermittently crashing since today morning 🙃
reminds me of the Facebook swizzling crash incident.
@Firebase pls help
Lorenzo 'kelset' Sciandra retweeted
We benchmarked GPT-6 models in DOOM by having LLM agents fight each other. Across 120 matches, we found:
- Astra had the highest win rate at 82.5%
- Sol made the fastest decisions at avg of 5.34s
- Luna had the most wins per dollar at 12.8
GitHub: github.com/Rootly-AI-Labs/ro…
@OpenAIDevs @rootlyhq
Lorenzo 'kelset' Sciandra retweeted
Benchmarks GPT-6 Sol & Luna:
• FrontierCode: 48.4% vs. Fable 5.1’s 48.7%, both at xhigh. $1.37 vs. $9.27 per task, roughly 85% cheaper.
• DeepSWE: 68.8% at max vs. Fable 5’s best result of 69.9% at xhigh. $2.74 vs. $13.41 per task, roughly 80% cheaper.
• AutomationBench: 33.2% at xhigh vs. Fable 5.1 with Opus 5 fallback at 31.4% on max. $0.27 vs. at least $2.45 per task.
GPT-6 Luna:
• DeepSWE: 66.6% at max vs. Fable 5’s 65.4% at medium. $0.22 vs. $6.09 per task, roughly 96% cheaper.
API pricing per million input/output tokens:
• Sol: $2 / $10
• Luna: $0.10 / $0.50
Lorenzo 'kelset' Sciandra retweeted
iPhone Duo support landed in agent-device 0.21.7
it's so annoying that agents need computer use / macOS desktop handling to toggle unfolded state.
thankfully @agent_device covers it all
Lorenzo 'kelset' Sciandra retweeted
Scammers found a way to make people drain their own wallets without sending them a phishing link.
They uploaded YouTube tutorials showing people how to build an AI crypto trading bot with Claude.
People followed the tutorial themselves.
Copied the code.
Deployed the smart contract themselves.
Funded it from their own wallets.
And approved every transaction themselves.
Except the “trading bot” had no trading logic.
It was built to send their ETH straight to the scammers.
224 wallets lost 274.6 ETH, worth about $517,000 when it was stolen.
The median victim lost 1 ETH.
Some victims even got an error after getting drained telling them to deposit another 50% to fix the bot.
They literally got people to build, fund and approve their own wallet drainer.
You've got to be very careful this days
Lorenzo 'kelset' Sciandra retweeted
It's safe to say that within 6-12 months we'll be able to do an entire day's work without touching our computer other than turning it on and off.
I built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is!
I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.
The Android team released v2 of their benchmark for LLMs: android-developers.googleblo…
not surprised to see GPT Sol and Astra on top (together with Fable) - matches my experience
(still waiting for a good eval for the Swift/SwiftUI side 🫠)
Lorenzo 'kelset' Sciandra retweeted
Distance yourself from people who play status and power games.
Invite people into your life that play value creation and wisdom sharing.
ok so i installed iOS 27.0 on my phone.... is it just me or is the virtual keyboard worse? like, actually less smooth?
Lorenzo 'kelset' Sciandra retweeted
musk too. three guys who dont particularly like each other (to put it mildly)
xitter.cf/elonmusk/status/209878…





























