Robert Zey

Senior .NET/Azure dev going deep on AI | C#, .NET Core, Azure | Sharing what actually works |

[lauren @poteto]

here's how i shipped 2,500 PRs last month to production

this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly

[lauren @poteto]

https://t.co/2Z8GabbwBv

[lauren @poteto]

i might be addicted to making games now

[Microsoft Learn @MicrosoftLearn]

The most valuable tech skill you could have is to keep learning as the tools change.

[Thariq @trq212]

We're adding support for AGENTS.md to Claude Code.

Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md.

You can toggle this behavior in /config.

[lauren @poteto]

poteto

[Nate Herk @nateherk]

This is only going to keep happening.

Build your teams and workflows to be model-agnostic.

[Maximilian @maxedapps]

@typesafeai released Jev.

I truly believe this is a game changing kind of AI model. No joke.

It does NOT replace LLMs. But in tandem with LLMs it feels like a missing building block. It makes the kind of applications you can build now SO much better and more powerful. And cheaper!

It's an AI model that's all about decision making. But not like old-school classifiers ("fraud or no fraud") but with flexibility you know from LLMs.

Feed some input (eg customer email, any other text, structured data) into it, define your questions ("which team should answer this email?") and dimensions ("sales, technical, fraud") and get back a response within milliseconds. No long reasoning, no exploding token costs.

Sure, that answer will still be generated by an LLM, complex questions may still require an (additional) LLM but this model is really mindblowing.

[Robert Zey @fortworthdev]

@BradDukeTX @bot Dead in the water, first time it's happened to me

[Programmer Humor @PR0GRAMMERHUM0R]

Two decades of education, undone by one autocomplete tab.

[Nate Herk @nateherk]

https://t.co/eOBYc1F7Bi

[Matt Pocock @mattpocockuk]

A great idea I'm stealing from @dexhorthy:

When you first start building a software factory, make it TINY.

Don't get it to triage every issue in your repo. Just do one per day.

Check its output. Adjust it. Keep going with your regular work.

As you begin to trust its judgment, get it to triage TWO issues per day instead. Then five. Then ten.

Start small. Adjust. Build trust. Expand.

[Robert Zey @fortworthdev]

Why Grok 4.7 is delayed matters way more than the countdown:

• RL over-penalizing length → model gives up early
• Inadequate self-correction → hallucinations slip through

That’s agentic AI in a nutshell: persistence and self-verification. Worth the wait if it actually solves the hard stuff.

https://t.co/xBxsqGcipZ

[Elon Musk @elonmusk]

@farzyness Grok 4.7 needs a few more days to cook.

We might have penalized response length too much (or something) in RL, as it still gives up on hard tasks (that it can do!) too early and isn’t yet sufficiently rigorous in checking its work.

[dex @dexhorthy]

til “/grill-me” can also be applied to breakfast - cheers @mattpocockuk

[SCR @SCR01111]

20 AI RESOURCES YOU SHOULD KNOW 📌

1. Hugging Face LLM Course
https://t.co/Xm4cM5VI0o

2. Google ML Crash Course
https://t.co/kpQ3bVGiAb

3. https://t.co/CmLFBHy8lC
https://t.co/pQYlmvSOBw

4. OpenAI Academy
https://t.co/Xmi4DBN8zR

5. Karpathy — Neural Networks: Zero to Hero
https://t.co/SX3lshunqK

6. Full Stack Deep Learning
https://t.co/t69H8xOlT3

7. Hugging Face Learn
https://t.co/dKahBuS4If

8. Microsoft AI for Beginners
https://t.co/V7Oilwt7nA

9. Made With ML
https://t.co/ffzMrwQ7u9

10. https://t.co/bq27x5UKTv
https://t.co/sVCmWuwR4U

11. Stanford CS229
https://t.co/2LBUqM7lOA

12. Stanford CS231N
https://t.co/M5YfWTx6pX

13. Stanford CS224N
https://t.co/QuXDEgkNwx

14. Google DeepMind Learning Hub
https://t.co/6422y9xajv

15. AWS Machine Learning
https://t.co/Da2tgaL0hc

16. PyTorch Tutorials
https://t.co/hEFAsWZCXJ

17. TensorFlow Tutorials
https://t.co/yhzGRIddcV

18. NVIDIA Deep Learning Institute
https://t.co/7rwzGqSnsi

19. Microsoft Learn AI
https://t.co/JTGUYHwbfU

20. Google Machine Learning
https://t.co/CCfEtGjqi3

Save this list.

Learn → Build → Ship.

[Mihail Eric @mihail_eric]

I’m excited to finally announce the newest edition my Stanford course 𝗧𝗵𝗲 𝗠𝗼𝗱𝗲𝗿𝗻 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿. It has been 9 months in the making.

Last November, with the release of Claude Opus 4.5, coding agents experienced a step function improvement in capability. We all felt it. The LLMs were more powerful, could reason for longer, solve harder tasks.

This year’s iteration of my course reflects the 2026 metamorphosis of software engineering.

My core belief is simple: AI-native developers of the LLM era are going to become the most important members of any software organization. I have designed my course to train this next generation of engineers.

𝗪𝗵𝗮𝘁’𝘀 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝘁𝗵𝗶𝘀 𝘁𝗶𝗺𝗲 𝗮𝗿𝗼𝘂𝗻𝗱

First, 85% of my Fall 2025 class material is being thrown out. The Fall 2026 syllabus reflects the core capabilities AI-native engineers must have: agent skills, advanced context engineering, MCP portals, agent-ready codebase principles, agentic code review, security, parallelizing background agents, software factories, and more.

Second, I am going to teach my students how to have software taste. Every student will be required to ship pull requests to production-grade, real-world codebases. The course is collaborating with the top open-source AI repos who will offer support and mentorship to students on how to meaningfully contribute to their projects.

This has never been done before in any university course so I am incredibly grateful to our OSS Partners: @browserbase, @HeyGen, @CopilotKit, @semgrep, @OpenHandsDev, @milvusio, @marimo_io, Pi, @crewAIInc, @warpdotdev, @vercel, @cmux, @arizeai, @UnslothAI, and @anyscalecompute.

𝗪𝗵𝗮𝘁’𝘀 𝘀𝘁𝗮𝘆𝗶𝗻𝗴 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲

I’m fortunate to again have AI software engineering leaders and founders as guest speakers to share their learnings from building top coding agent products. Thank you to @leerob from @cursor_ai, @bcherny of @claudeai code, @EnoReyes of @FactoryAI, @silasalberti of @cognition, @0xine of @semgrep, Rajesh Bhatia of @Cloudflare , @amasad of @Replit, and @eladgil.

All resources will be available online. All classes will be available to the public.

9/22 on Stanford campus. See you in class. 

https://t.co/wTokHyUMsz

[ClaudeDevs @ClaudeDevs]

We're open-sourcing Claude Commerce Agents.

This is a blueprint for building shopping and merchant agents, with reference implementations across retail, travel, telecom, and entertainment.

[Sundar Pichai @sundarpichai]

Today we’re introducing a new 3.8 Flash model, our 3rd Flash release in just 6 wks.

It delivers significant leaps from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. On DeepSWE v1.1, it outperforms most larger frontier models in autonomously solving complex engineering problems end to end, at a fraction of the cost.

More details here: https://t.co/4YkKkdKQvu

[Google @Google]

Introducing Gemini 3.8, our best reasoning & coding model yet.

By leveraging long-running agentic loops, we’re building on the momentum of 3.7 Flash from just three weeks ago to release two new 3.8 variants:

Meet Gemini 3.8 Flash and Gemini 3.8 Flash Cyber 🧵

[Mark Zuckerberg @finkd]

Muse Spark 1.3 is rolling out today with frontier performance almost too cheap to meter. This is the biggest jump we've made so far on coding and agentic work. Try it in Muse Code and our API.

Next up 🍉 and Muse Spark open weights releases coming soon.