Why Canada Blasted a Huge Hole Outside its Parliament YouTube video by The B1M

Wow

youtu.be/IxFcNOmND00?... #canada

I just published a deep-dive into the 250-hour build behind syntaqlite, a SQLite formatter and LSP I built using AI agents.

AI agents were the only reason built this after 8 years of wanting but there's a psychological toll to AI-assisted engineering.

The post-mortem:
lalitm.com/post/buildin...

"The failure mode isn't malice. It's convenience."

ergosphere.blog/posts/the-ma...

[2603.20639] Agentic AI and the next intelligence explosion share.google/Fbbak2LPf0I7...

Harness design for long-running application development Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

www.anthropic.com/engineering/...

Gemini CLI has plan mode now. I don't know how good it is but this was the main barrier to me using it other than as a reviewer for Claude Code work.

Datadog, Block, and Cloudflare All Abandoned the Default MCP Pattern. Here’s What They Use Instead Comparing traditional, code mode, and layered query patterns — with real benchmarks on the HackerNews API

Read “Datadog, Block, and Cloudflare All Abandoned the Default MCP Pattern. Here’s What They Use Instead“ by Tanmay Deshpande on Medium: medium.com/data-science...

LangChain Open-Sourced the Architecture Behind Coding Agents. Here's What It Actually Reveals. The same four components that power Claude Code are now open source, inspectable, and model-agnostic by design.

Read “LangChain Open-Sourced the Architecture Behind Coding Agents. Here's What It Actually Reveals.“ by Ari Vance on Medium: ai.gopubby.com/langchain-op...

100% - Shipping poor llm code is a choice

Image

Say hello to Gemini Embedding 2, our new SOTA multimodal model that lets your bring text, images, video, audio, and docs into the same embedding space! 👀 x.com/OfficialLoga...

Very disturbing implications for a couple of places where I’ve lived, and encouraging ones for the place where I’m from.

From Pew: “We asked people around the world to rate the morality and ethics of others in their country.”

Closing session at another great ISPAmerica. Great war stories.

share.google/oaY4TdJMHB4r...

University of Waterloo @UWaterloo x.com This account is no longer active. Looking to stay connected with the University of Waterloo? • News: uwaterloo.ca/news/ • Bluesky: uwaterloo • IG: uofwaterloo • FB: university.waterloo • LI: uwaterloo Thank you 9:41 AM • 2026-02-27 • 1.5M Views

Congrats University of Waterloo for leaving X!

Make sure to follow them here @uwaterloo.ca

Security boundaries in agentic architectures - Vercel A framework for drawing security boundaries in agentic architectures. Most agents run with zero isolation between the agent and the code it generates. Learn where to draw the boundaries, from secret i...

From @vercel.com: An agent performing support duties for a specific customer should receive a tool scoped to that customer's data, not a tool that accepts a customer ID parameter, since that parameter is subject to prompt injection.

vercel.com/blog/securit...

technoyoda.github.io/agent-search...

Worth reading #ai #agent

Google’s A2UI Protocol Just Changed How AI Agents Build User Interfaces — Here’s My First Project… Two weeks ago, Google open-sourced something that might reshape how we think about AI-generated interfaces: A2UI (Agent-to-User Interface).

Read “Google’s A2UI Protocol Just Changed How AI Agents Build User Interfaces — Here’s My First Project…“ by Pawel on Medium: medium.com/@meshuggah22...

Modular: The Claude C Compiler: What It Reveals About the Future of Software Compilers occupy a special place in computer science. They're a canonical course in computer science education. Building one is a rite of passage. It forces you to confront how software actually works...

www.modular.com/blog/the-cla...

rhai.rs

GitHub - rune-rs/rune: An embeddable dynamic programming language for Rust. An embeddable dynamic programming language for Rust. - rune-rs/rune

github.com/rune-rs/rune

GitHub - pydantic/monty: A minimal, secure Python interpreter written in Rust for use by AI A minimal, secure Python interpreter written in Rust for use by AI - pydantic/monty

This is interesting, a 'safe' Python interpreter for use by AI agents. I guess because the LLMs know Python better than Rune or RHAI?

github.com/pydantic/monty

In the last 48 hours, Musk's reactions to the Epstein release show exactly why he bought Twitter.

He's used the platform to call coverage of his emails with Epstein as "lies," elevated his fans who have defended him, and gotten positive reinforcement from his AI chatbot.

He should actually read the book.

At what point does Poilievre look at how Carney handles things and think, crap, I'm really not the person the country needs now?

btrfs

CARNEY: “.. You cannot live within the lie of mutual benefit through integration when integration becomes the source of your subordination.” 🔥

This is the best speech, just from a pure rhetoric perspective - its sophistication and persuasiveness - that I've seen a politician deliver in a good long while. Really recommend watching or reading the whole thing.

The year everything changed Far from my best years being behind me, it feels as though everything in my life has been leading to this moment: building a completely new category of product where the most useful lessons come not f...

networkgames.fyi/the-year-eve...

If a restaurant served you a perfectly-cooked steal with a cockroach on it, would your feedback be "It was perfectly cooked, but there was a cockroach on it"?

Or would you just see the cockroach and conclude the steak's inedible?

In case you're wondering what impact bugs have on user feedback.

I've published a post on better prompting for LLMs: "Prompting 101: Show, don't tell"

This is inspired by a similar post from an internal prompt engineering training series I wrote for Mercury:

www.haskellforall.com/2026/01/prom...

1 year: It will become undeniable that LLMs write good code 1 year: We’re finally going to solve sandboxing 1 year: A “Challenger disaster” for coding agent security 1 year: Kākāpō parrots will have an outstanding breeding season 3 years: the coding agents Jevons paradox for software engineering will resolve, one way or the other 3 years: Someone will build a new browser using mainly AI-assisted coding and it won’t even be a surprise 6 years: Typing code by hand will go the way of punch cards

I joined the Oxide and Friends annual predictions podcast episode this week - here are my 1, 3 and 6 year predictions for AI and LLMs (and Kākāpō parrots) simonwillison.net/2026/Jan/8/l...