Web Directions (@webdirections.org) Bsky

Nick Beaugeard: AI demos are easy. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 day ago 0 0 0 0

Slop Is Not Necessarily The Future\ A couple of years ago, “slop” became the popular shorthand for unwanted, mindlessly generated AI content flooding the internet including images, text, and spam. Simon Willison helped popularize the term, though it had been circulating in engineering communities in the years prior. I want to argue that AI models will write good code because of economic incentives. Good code is cheaper to generate and maintain. Competition is high between the AI models right now, and the ones that win will help developers ship reliable features fastest, which requires simple, maintainable code. Good code will prevail, not only because we want it to (though we do!), but because economic forces demand

1 day ago 0 0 0 0

Daniel Nadasi: (as submitted in the original form, let me know if lost) AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

3 days ago 0 0 0 0

Jason Cornwall: Most “AI gives you 10x productivity” stories assume coding is the bottleneck. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

4 days ago 0 0 0 0

AI in production isn't about the model. Abdul Karim & Jack Silman on the full engineering pipeline: integration, testing, observability, everything else. AI Engineer Melbourne, June 3-4 webdirections.org/ai-engineer

4 days ago 1 0 0 0

Theodoros Galanos: Large language models excel at code—but engineering isn't just code. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

4 days ago 0 0 0 0

Rob Manson: What's the role of the web in our modern AI future... AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

5 days ago 0 0 0 0

Jakub Riedl: AGENTS.md started as a simple way to guide coding agents, but many teams are discovering that a default or poorly written one can actually make agents worse. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

5 days ago 0 0 1 0

Thiago Shimada Ramos: What does it look like to build AI agents that never touch the internet? AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

5 days ago 1 0 0 0

When do multi-agent systems add value? Anannya Roy Chowdhury shares real metrics from AWS on where the complexity payoff exists. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

6 days ago 2 0 0 0

Simon Knox: Cloud outages used to mean your site went down, maybe you couldn’t deploy. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

6 days ago 0 0 0 0

AJ Fisher: The smartest model doesn’t always win. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

6 days ago 0 0 0 0

Chris Rickard: Legacy Software powers the world - from banking to utilities and government. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 week ago 0 0 0 0

Eight years of wanting, three months of building with AI – Lalit Maganti For eight years, I’ve wanted a high-quality set of devtools for working with SQLite. Given how important SQLite is to the industry1, I’ve long been puzzled that no one has invested in building a really good developer experience for it2. A couple of weeks ago, after ~250 hours of effort over three months3 on evenings, weekends, and vacation days, I finally released syntaqlite (GitHub), fulfilling this long-held wish. And I believe the main reason this happened was because of AI coding agents4. Of course, there’s no shortage of posts claiming that AI one-shot their project or pushing back and declaring that AI is all slop. I’m going to take a

1 week ago 0 0 0 0

Components of A Coding Agent – by Sebastian Raschka, PhD In this article, I want to cover the overall design of coding agents and agent harnesses: what they are, how they work, and how the different pieces fit together in practice. Readers of my Build a Large Language Model (From Scratch) and Build a Large Reasoning Model (From Scratch) books often ask about agents, so I thought it would be useful to write a reference I can point to. More generally, agents have become an important topic because much of the recent progress in practical LLM systems is not just about better models, but about how we use them. In many real-world applications, the surrounding system, such as tool use,

1 week ago 0 0 0 0

Moin Zaman: De-identifying text is easy to demo and surprisingly hard to ship. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 week ago 0 0 0 0

The Cathedral, the Bazaar, and the Winchester Mystery House – O’Reilly In 1998, Eric S. Raymond published the founding text of open source software development, The Cathedral and the Bazaar. In it, he detailed two methods of building software: The ideas crystallized in The Cathedral and the Bazaar helped kick off a quarter-century of open source innovation and dominance. But just as the internet made communication cheap and birthed the bazaar, AI is making code cheap and kicking off a new era filled with idiosyncratic, sprawling, cobbled-together software. Meet the third model: The Winchester Mystery House. Source

1 week ago 0 0 0 0

Notion ships sandboxed workers in their agent platform. Adam Hudson on safely executing third-party code inside agents. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 week ago 1 1 0 0

Annie Vella: AI assistants ship more code but erode the craft that makes engineering joyful. How do we build systems that sustain both? AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 week ago 1 0 0 0

Mic Neale: The current AI stack has a dependency most of us don’t talk about: a handful of closed models from a handful of providers, and an API call standing between every agent and every action. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 week ago 0 0 0 0

AI in production isn't about the model. Abdul Karim & Jack Silman on the full engineering pipeline: integration, testing, observability, everything else. AI Engineer Melbourne, June 3-4 webdirections.org/ai-engineer

1 week ago 1 0 0 0

Geoff Huntley: Software development as we knew it is dead. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 week ago 0 0 0 0

Matthew Gillard: The email didnt have what I submitted... AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 week ago 0 0 0 0

Yasith Fernando: AI coding tools are rewriting what it means to build software. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

1 week ago 0 0 0 0

damn claude, that’s a lot of commits | AI Focus The week of September 29 2025, there were 27.7 million public commits on GitHub. Claude Code accounted for 180,000 of them, about 0.7%. By the week of March 16 2026, total weekly commits had grown to 57.8 million (itself a 2.1x increase, likely driven in part by AI tooling), and Claude Code accounted for 2.6 million, or 4.5%. All AI coding tools combined now sit at roughly 5% of every public commit on GitHub. For context, GitHub’s Octoverse 2025 report recorded 986 million code pushes for the year, with monthly pushes topping 90 million by May 2025, and that trajectory hasn’t slowed down. Claude Code went from 0.7% to 4.5%

1 week ago 0 0 0 0

Encoding Team Standards I have observed this pattern repeatedly. A senior engineer, when asking the AI to generate a new service, instinctively specifies: follow our functional style, use the existing error-handling middleware, place it in lib/services/, make types explicit, use our logging utility rather than console.log. When asking the AI to refactor, she specifies: preserve the public contract, avoid premature abstraction, keep functions small and single-purpose. When asking it to check security, she knows to specify: check for SQL injection, verify authorization on every endpoint, ensure secrets are not hardcoded. A less experienced developer, faced with the same tasks, asks the AI to “create a notification service” or “clean up this code” or

1 week ago 0 0 0 0

Quantization from the ground up | ngrok blog Qwen-3-Coder-Next is an 80 billion parameter model 159.4GB in size. That’s roughly how much RAM you would need to run it, and that’s before thinking about long context windows. This is not considered a big model. Rumors have it that frontier models have over 1 trillion parameters, which would require at least 2TB of RAM. The last time I saw that much RAM in one machine was never. But what if I told you we can make LLMs 4x smaller and 2x faster, enough to run very capable models on your laptop, all while losing only 5-10% accuracy. Source

2 weeks ago 0 0 0 0

Simon Knox: Cloud outages used to mean your site went down, maybe you couldn’t deploy. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

2 weeks ago 0 0 0 0

We Rewrote JSONata with AI in a Day, Saved $500K/Year | Reco A few weeks ago, Cloudflare published “How we rebuilt Next.js with AI in one week.” One engineer and an AI model reimplemented the Next.js API surface on Vite. Cost about $1,100 in tokens. The implementation details didn’t interest me that much (I don’t work on frontend frameworks), but the methodology did. They took the existing Next.js spec and test suite, then pointed AI at it and had it implement code until every test passed. Midway through reading, I realized we had the exact same problem – only in our case, it was with our JSON transformation pipeline. Long story short, we took the same approach and ran with it. The

2 weeks ago 0 0 0 0

Prem Pillai: Every engineering team trying to automate developer workflows with AI agents hits the same wall: the iteration tax. AI Engineer Melbourne, June 3-4 aiengineer.webdirections.org

2 weeks ago 1 0 0 0

Posts by Web Directions