If I understood it correctly, is it to design and build “something” that can work (more and more) autonomously?

We called it prompt engineering. Then context engineering. What is going to be the next shift?

dev.to/danilop/from...

Yes. To reduce the trade-off, there’s lots of research on how to avoid the quadratic growth of transformer’s attention.

Efficiency is definitely an important perspective. A non functional requirement to add to any AI-related project.

We called it prompt engineering. Then context engineering. What is going to be the next shift?

dev.to/danilop/from...

Understanding LLMs by Building One 👉 We use large language models every day, but what actually happens inside them?

danilop.github.io/micro-gpt-an...

GitHub - danilop/micro-gpt-and-beyond: Build a GPT from scratch, one concept at a time, from pure Python to PyTorch, JAX, MLX, and production serving. Inspired by Andrej Karpathy's microGPT. Build a GPT from scratch, one concept at a time, from pure Python to PyTorch, JAX, MLX, and production serving. Inspired by Andrej Karpathy's microGPT. - danilop/micro-gpt-and-beyond

You can use the web tutorial online or clone/fork the repo to run the code as in the video. Let me know here or in an issue if something is not clear or should be improved!

github.com/danilop/micr...

GitHub - danilop/walk-the-code: Interactive line-by-line code tutorial viewer with multi-language support and Mermaid diagrams Interactive line-by-line code tutorial viewer with multi-language support and Mermaid diagrams - danilop/walk-the-code

The interactive web tutorial is powered by walk-the-code, a standalone line-by-line code tutorial viewer with multi-language support, chapters, Mermaid diagrams with per-line node highlighting, and stale annotation detection:

github.com/danilop/walk...

Some the internals explain the behavior (and issues) we observe. That’s why I build these online labs, initially inspired by Andrej Karpathy's microGPT, to help explore simple code bases that train, fine-tune, and explore present and future grands of LLMs.

Understanding LLMs by Building One 👉 We use large language models every day, but what actually happens inside them?

danilop.github.io/micro-gpt-an...

‪
🌳 Do you want to contribute to research on how humans perceive forests? Take this quick, anonymous 10-min survey 🌲

👉 www.biodiful.org#/forest

This will help us explore how people experience forest biodiversity!

Please share on 🦋 & tag @biodiful.bsky.social to reach more participants 🙏💚

🌐🌍🦤🦑🪴🍁🧪

Building Wispr with Kiro: A Spec-First Approach to Swift Development Developer Advocate @ AWS. I write about the cloud & Swift<br/>(opinions are my own)

How I built a production-ready macOS voice dictation app in 1.5 days using AI-assisted development, without writing a single line of code myself.

stormacq.com/2026/03...

#swiftlang #kiro #aiagents

And now I added an example of INT8 quantization for inference.

For fun, I added a "micro" masked diffusion text model variant (MDLM/LLaDA)... Now names emerge from noise :)

The progression goes from raw first principles in pure Python to framework-powered GPU code using PyTorch, JAX, and MLX.

Inspired by Andrej Karpathy's #microGPT, here are eight implementations of the same tiny GPT language model, each version teaching something different about how neural networks are built, trained, and run:

github.com/danilop/micr...

Each pattern involves trade-offs that we discuss so that attendees leave with both practical criteria for their current deployments and a framework for evaluating new approaches as this space continues to evolve.

In this session, we look at possible solutions including deferred loading, progressive disclosure, and runtime controls. These approaches keep detailed definitions out of context until the agent needs them and implement guardrails around how agents can use tools.

A single MCP server can expose tens of tools, and each tool definition consumes hundreds of tokens. Connect a few servers and a significant portion of your context window is gone before any user input is processed. The effect is that AI agent accuracy drops as tool count grows.

Here are the slides for my session today!

Context pressure with MCP: Patterns and trade-offs

danilop.s3.eu-west-1.amazonaws.com/Presentation...

Hey, I’ll be speaking at #MCPconference London on 11–12 February. My session:

Context pressure with MCP: Patterns and trade-offs

There's a free ticket for my network: luma.com/mcplondon202...

Reach out if you're there! I look forward to the tech chat :)

They need help for building more? :)

So building tech debt.

Also, these is an AWS Serverless MCP server that provides info on how to build with a serverless stack. Did you try it?

Very interesting analysis. What I found works best with current agents and models is to give them a link to the reference implementations they should use. So saying something like “use the API Gateway form this sample but with these changes” or “use this Cognito implementation but with this SSO”.

AWS Weekly Roundup: Kiro CLI latest features, AWS European Sovereign Cloud, EC2 X8i instances, and more (January 19, 2026) | Amazon Web Services At the end of 2025 I was happy to take a long break to enjoy the incredible summers that the southern hemisphere provides. I’m back and writing my first post in 2026 which also happens to be my last...

📰🚨 AWS Weekly Roundup: Kiro CLI latest features, AWS European Sovereign Cloud, EC2 X8i instances, and more (January 19, 2026)

#AWSNewsBlog #AWSCommunityDay #reInvent #AWSBuilderCenter #SSACommunity

AWS Weekly Roundup: AWS Lambda for .NET 10, AWS Client VPN quickstart, Best of AWS re:Invent, and more (January 12, 2026) | Amazon Web Services At the beginning of January, I tend to set my top resolutions for the year, a way to focus on what I want to achieve. If AI and cloud computing are on your resolution list, consider creating an AWS…

Here's my AWS Weekly Roundup 👉 AWS Lambda for .NET 10, AWS Client VPN quickstart, Best of AWS re:Invent, and more (January 12, 2026)

ift.tt/iwO2SgI

#AWS #News #Serverless #VPN

How I Used Kiro to Optimize Its Own MCP Configuration I had a problem. My Kiro setup had accumulated 14 MCP servers over time: AWS tools, web automation,...

I had a problem. I had accumulated too many MCP servers over time. So I asked Kiro to improve its own configuration and group tools into Powers that are loaded in context only when needed. Self-optimization is a new pattern.

dev.to/aws/how-i-us...

#AWS #Kiro #DevEx #AI

That’s better!

Hey, Amazon Science is on Bluesky! Welcome :)

@amazon-science.bsky.social