
AI Enthusiast 💡 | Product Developer @datatech | Cyclist 🚴♂️ | Techie 🤖
Phoenix
Joined March 2023
- Tweets1.7K
- Following146
- Followers24
- Likes6.7K
Kevin Young retweeted
The PR reviewer just lost the first read
Claude Code Review posts findings before people look
Several agents read each change with the code around it
A verify step drops what does not hold up
In the March preview a review took about 20 minutes
Most reviews now finish in 6 to 10 minutes
The agents file the bug report now
The reviewer just picks what to fix
Full breakdown below
Kevin Young retweeted
Need fresh design inspo? Start with these 9 resources👇
1. inspora.design — Your daily design inspiration
2. land-book.com — Landing page inspo
3. Backgrounds.supply — Custom backgrounds
4. mobbin.com — App UI inspiration
5. obsidianui.dev — Animated React components
6. reelfolio.io — Animated showreels
7. bencho.dev — Interactive UI components
8. minimal.gallery — Minimal website inspiration
9. refero.design — Real product UI
Save this list. You’ll need it🔖
Stripe has integrated Link and Stripe MCP into Claude Duet.
Link handles purchases using a virtual card after the user approves each transaction. Stripe MCP lets users send invoices and payment links, issue refunds, manage products and prices, and analyze revenue inside Duet.
Claude Duet is currently a research preview with a waitlist for US Pro and Max subscribers.
We’re working with Anthropic to help you run your businesses inside Claude Duet.
• Make purchases with @link
• Issue refunds and understand business trends with the Stripe MCP
Kevin Young retweeted
From GTC Berlin today: "And so by moving this into the supply chain, the speed by which we can turn on, go from installation, arrival of computing to production of tokens will go from many months, we think something along the lines of four to five months down to about a month. So this is a complete transformation of the world supply chain and this will change the way that people install and build data centers and hopefully as a result velocity goes up, the wasted idle compute, the wasted idle capex will reduce and everybody becomes more profitable." $NVDA
Nvidia GTC Berlin 2026: Jensen Huang Full Keynote, Yahoo Finance, October 21, 2026
Open is better.
Agent Observability with #OpenTelemetry support is now GA. See what your agents are doing and what they cost your teams, on the same open standards as the rest of your stack.
🔗: grafana.com/blog/observabili…
#ObservabilityCON
Kevin Young retweeted
You can also use this to make VSCode/Cursor/Zed faster.
In your VSCode/Cursor config:
"𝚓𝚜/𝚝𝚜.𝚝𝚜𝚍𝚔.𝚙𝚊𝚝𝚑": "𝚗𝚘𝚍𝚎_𝚖𝚘𝚍𝚞𝚕𝚎𝚜/𝚝𝚜𝚛𝚜/𝚋𝚒𝚗/𝚝𝚜𝚛𝚜"
(for Zed: lsp.typescript-ls.binary.path)
Introducing tsrs: a Rust port of the TypeScript compiler 🦀
We are not forking TypeScript!
◆ In close collaborating with the TypeScript team
◆ Up to 8x faster than TS 7.0 & ~70% less memory
◆ Runs in WASM, so it works in your browser & on Workers
◆ Soon part of the Oxc toolchain
npx tsrs
blog.cloudflare.com/typescri…
Kevin Young retweeted
📤 Make exporting table data effortless.
The 𝗦𝗵𝗮𝗱𝗰𝗻 𝗗𝗮𝘁𝗮𝗧𝗮𝗯𝗹𝗲 𝗘𝘅𝗽𝗼𝗿𝘁 blocks feature:
• 📄 Export to CSV, Excel & JSON
• ⚙️ Easy export controls
• 📊 Export structured table data
• 🎨 Customizable UI
Built with React, Tailwind CSS & shadcn/ui.
Explore the blocks 👇
Kevin Young retweeted
BOOM! Jev + safety this time.
150K decisions for prompt safety, response safety and refusal routing.
Built on NVIDIA Aegis 2.0. Source labels and Jev predictions, kept side by side.
huggingface.co/datasets/Mazi…
Kevin Young retweeted
An agent writes the code now. Do you still need an IDE?
You do if you want to understand and verify what the agent did.
🎥 In our new video, we talk about the role of an IDE now that humans aren't the only ones working on the code. youtu.be/AHFGMkzrfwM
Kevin Young retweeted
Developers care how the game was built. Players care whether it’s worth playing.
Gregory and Paul discuss what happens when pride in the craft meets the economics of AI.
Kevin Young retweeted
At some point I think AI is going to become my manager. I will effectively work for AI. :(
Kevin Young retweeted
Unreal Engine shipped an official MCP.
Unreal MCP lets a language-model assistant edit the scene inside the Unreal editor
The viewport is an empty gridded ground. A red-green-blue move widget stands in the middle. A black panel sits on the right. The window title says Load Unreal MCP, and a line at the bottom still says accept edits. This is the official hook Epic wrote into the Unreal 5.8 docs. Once connected, an MCP-compatible coding assistant can spawn Actors, set lights, make material instances, inspect Slate widgets, or run automation tests. It can also tell you what you currently have selected. For people building scenes and materials in Unreal, the assistant can edit the project in front of it, instead of writing somewhere else and pasting it back.
xitter.cf/UnrealEngine/status/21…
dev.epicgames.com/documentat…
The docs still mark it experimental. A lot of features are missing, and the interface will change. It listens on this machine by default, with no login. Don't open it to the outside.
Unreal Model Context Protocol (MCP) provides an official, Epic-supported way to connect your favorite agentic LLM tools directly to Unreal Engine🤝
Built on the open MCP standard, it enables agents to take action in your projects using the capabilities exposed by each editor—so you can use compatible agentic coding tools or build your own integrations, skills, and workflows around how you create: epic.gm/ue-mcp-docs
Kevin Young retweeted
One thing I find interesting about AI personalization is how much it still depends on what we explicitly tell a system.
Our preferences are often more subtle than that. Sometimes we know what feels right before we can explain why.
Sabi’s approach to understanding these signals through Brain AI Interfaces opens up some fascinating possibilities.
Especially as AI becomes more autonomous, the ability to understand human preferences and intent could become a meaningful part of building systems we genuinely trust.
Kevin Young retweeted
A KPMG survey finds that 89% report measurable value from AI, but only 12% consistently assess that value against its cost.
The figures raise a question: what can organizations conclude about AI economics if costs and benefits are not compared consistently?
Microblog @antgrasso
In its Global AI Pulse Q3 2026, KPMG reports that 61% review AI costs during approval and 59% monitor them once systems are running.
Consider an AI application that processes supplier invoices.
The finance team may know how much it costs each month. But how much time does it save once the manual corrections are taken into account?
Without that comparison, deciding whether to expand the application is harder.
Among organizations reporting established ROI, KPMG finds that 48% consistently compare AI value with cost.
Financial control tells an organization what it spends. Connecting cost to results helps it decide whether further investment makes sense.
#AIEconomics #AIManagement
Kevin Young retweeted
Can working at a successful company hurt your career?
In this week's episode, Kaila and Kyle discuss the potential career pitfalls of working at a successful org, and how to avoid the "trap of success" when you do.
Tune in here: permylastemailshow.com/the-t…
There are two types of fools during this cycle imo. There’s the smart-sounding “Ed Zitron” type, ideally with a posh British accent, questioning the value of the whole AI thing as vaporwave and utterly useless while using AI to generate all their arguments. AI is clearly transformative and enormously useful and productivity-enhancing.
There’s the second type. They are actually smart but poor at public speaking and explaining themselves, and stutters a lot. They are either directly building the tech or deeply invested in the vision. They are absolutely right that AI will be transformative, but make the mistake in thinking that it'll all happen right away sweeping across society, ignoring the hurdles to rapid adoption.
There may come a time in the coming months, when the first type looks like geniuses and feel fully vindicated, but in the long time it's the second type that will actually be proven right. As usual, timing is everything.































