Jordi Corbilla 🇬🇧

Practical engineering notes on systems, automation, data workflows, and applied AI.

[Khairallah AL-Awady @eng_khairallah1]

this is f*cking gold

Andrej Karpathy joined Anthropic five weeks ago.

A friend on his team just showed me the exact LOOPS.md file he actually uses.

I dropped it into my setup. The very first response was different.

Not slightly different. Completely different.

Claude stopped giving generic answers and started working exactly the way I think.

You don't talk to the model anymore. You build the system that talks to the model for you.

Bookmark it before it gets lost in your feed.

Read it now, then check the article below.

[Jordi Corbilla 🇬🇧 @thunderjordi]

https://t.co/MUPTLkHM6X

[BBC News (UK) @BBCNews]

Ford rehires human engineers after AI fails to match quality checks https://t.co/qCXegzDALN

[Hasan Toor @hasantoxr]

Loop Engineering is the next step after prompt engineering.

Most people still use Claude Code, Codex, Cursor, or Grok like a chat box:

Prompt.
Wait.
Copy.
Fix.
Prompt again.

This repo shows the next step:

You stop prompting the agent.

You design the loop that prompts the agent for you.

Inside:

→ Daily triage loops
→ PR babysitter loops
→ CI sweeper loops
→ Dependency sweeper loops
→ Changelog drafter loops
→ Post-merge cleanup loops
→ Issue triage loops

It also gives you CLIs to:

• Scaffold a loop
• Estimate token cost
• Audit if your repo is ready
• Add memory/state
• Add human handoff
• Add verification gates
• Run agents safely through GitHub Actions

The wild part is the shift in thinking.

Prompt engineering was about writing better instructions.

Loop engineering is about building a system where agents keep working, checking, fixing, and escalating without you babysitting every step.

This is what AI coding looks like when it stops being a chat session and starts becoming an operating system for software teams.

Repo: https://t.co/2USzC6KHUt

[Jordi Corbilla 🇬🇧 @thunderjordi]

https://t.co/6i5mEmiuZu

[MIT CSAIL @MIT_CSAIL]

A free 30-minute guide to mastering Claude Code: https://t.co/DBAkVyT2K1

[Khairallah AL-Awady @eng_khairallah1]

Anthropic engineer:

"You can build 5 assistants in one afternoon. Each one handles a task you've been doing manually every single day."

this is one of the best workflows I've seen in a long time

in this video he breaks down exactly how most people are using Claude:

- the 14% you lose to CLAUDE.md before typing a word
- the plugins that 95% of users have never installed
- the workflows that run without you typing a single prompt
- why starting every chat from zero is the slowest way to use Claude

if you've been starting every Claude conversation from scratch like it's never met you before, you're missing at least 20 features. probably 24

instead of another show tonight, watch this

make sure to bookmark it before it gets lost in your feed

the guide is in the article below

[Doug Finke @dfinke]

Modules:

Memory, State, and Evaluation
https://t.co/6KEfjS5Nit

Multi-Agent Systems and Orchestration
https://t.co/3wMSo7EdS7

Governance, Guardrails, and Operations
https://t.co/caIcQHao52

#AI #Agents #AgenticAI #MCP #Copilot #MicrosoftLearn

[Jeffrey Snover @jsnover]

I've said it before, I'll say it again.
If you aren't following @dfinke , you are making a mistake.
Doug is absolutely SPOT ON with this post.
I was actually in the process of writing something very similar.

[Elon Musk @elonmusk]

Pretty good progress

[BuBBliK @k1rallik]

Everyone keeps saying AI gives them garbage. Anthropic just proved the problem is you, not the model.

This 24 minute video rebuilds one prompt from useless to flawless. Save it for the evening with tea - now that Opus 4.8 is here, getting this is everything.

[Satya Nadella @satyanadella]

We've redesigned Copilot to be simpler, faster, and more intuitive, to help keep you in the flow of your work.

Try it out: https://t.co/iBuMPZ6L4b

[Movez @0xMovez]

Anthropic AI engineer just dropped a live masterclass on how to ship a team of production‑ready AI agents.

37 minutes. Free. From the Anthropic team.

here’s what she covers:

• 3 building blocks: brain, hands, sessions
• server-side loop, so nothing breaks on refresh
• agent teams shipping to production 10–15x faster
• why agents die before production

brain (persona) + hands (environment) + sessions = a production agent out of the box.

most people are still babysitting fragile agent scripts, while the people who figured this out ship agents that just stay running.

Watch this workshop, then read the full guide below.

[Alex Veremeyenko @alex_verem]

Microsoft didn't cancel Claude Code because it was bad.

They canceled it because it was TOO GOOD.

Engineers loved it so much that 84-95% used it monthly. Costs hit $500-$2,000 per person. Uber's entire $3.4B AI budget evaporated in 4 months.

The finance department killed what the engineering department unanimously praised.

Read that story again slowly.

AI tools are now so productive that companies literally cannot afford to let their employees use them freely.

This is the most bullish signal for solopreneurs I've ever seen.

Big companies will throttle, restrict, and ration AI access to control costs. Their engineers will be stuck on watered-down internal tools.

Meanwhile, you're sitting at home with Pro access to every frontier model on the planet for the price of a Netflix subscription.

The playing field isn't leveling. It's inverting.

[Dave McCollough @davemccollough]

If you’re planning on taking the Microsoft AB-900 certification, feel free to use my notes!

https://t.co/cWiLIZBz8t

[Alexandre Mutel @xoofx]

I'm thrilled to release CodeAlta - one of the first efficient AI coding-agent TUIs built entirely in C#/.NET 🚀

I've been developing and using it daily for the past 3 months, and I hope you enjoy it as much as I do! 🤗

Retweets are highly appreciated! 🙏

CodeAlta brings you a beautiful, colorful timeline interface, multiple threads in the same workspace, a real prompt editor experience, quick file viewing/editing with syntax highlighting, in-app model provider configuration, a multi-agent-ready environment, and much more! ✨

[Qwen @Alibaba_Qwen]

👀👀

[Elon Musk @elonmusk]

SpaceX is actively hiring world-class engineers/physicists for SpaceXAI, even if you have zero prior experience in AI. Smart humans figure it out fast.

Please send an email with ~3 bullet points demonstrating evidence of exceptional ability to [email protected].

[Visual Studio @VisualStudio]

Want faster .NET apps?
This VSLive! Las Vegas clip explains why caching plays such a big role in application performance.
Watch the full video:
https://t.co/FtJhbMrtQ5

[Visual Studio Code @code]

The new @code release adds Mermaid diagram rendering directly in the Markdown preview.

The Integrated Browser also now supports HTML file previews and drag-to-select for pulling multiple page elements into chat context.