VOL 2, ISSUE 36 · 19 SEPTEMBER 2026 Space to be human Last week I wrote about leaving the Mac for Omarchy after 25 years, and ended on being one step closer to a co-operating system that works with me instead of one I have to work around. A lot of this week comes back to that: creating my own co-operating system from the tools available. This past week has been a major 'back to school' week for the family, including new travelling times, and a massive storm that came through the area mid-week...
about 20 hours ago • 6 min read
VOL 2, ISSUE 34 · 4 SEPTEMBER 2026 Handing off the 60% If planning, researching and strategising take up, say, 40% of a task, then 60% is left to execute and iterate. That 60% can take up 100% of your available time if you're doing it manually. This is the week that argument stopped being theoretical for me. The kids are home, my partner is at work, and the writing happens in the gaps — text the agent, deal a new hand of Go Fish, check what came back. It's also the week I started calling...
16 days ago • 7 min read
VOL 2, ISSUE 33 · 28 AUGUST 2026 Dear Reader, If this issue looks different from the ones you are used to, that is because it is. Signal Over Noise has moved to a site-first setup, and the newsletter now follows the site rather than the other way round. If you missed it, here is what changed and why. The magic in agent interfaces still needs an off switch "Ship it" is an attractive interface for a workflow that pushes code, prepares publication processes and starts a series of reviews. It is...
23 days ago • 1 min read
Dear Reader, An update on Signal Over Noise. I'm approaching two years of writing Signal Over Noise. I never really wanted this newsletter to be another 'AI thing of the week' publication. There are loads of those going around, and mostly for good reason — there's a lot of stuff to learn and get through. But I started this as a 'building in public' kind of journal after the end of a years-long work contract that left me wondering what to do with myself. Since then I've learned so much. Those...
23 days ago • 3 min read
Field Note: One foot on the brake, one on the gas Two things happened at OpenAI in the same week, and they don’t sit together comfortably. On August 18, OpenAI said it had paused two weeks of training on the newest models it plans to release. Its biggest planned training run is still on hold. The company gave two reasons: its own models breaking into Hugging Face during an internal test in July, and early signs that an upcoming model called Astra may reach the “Critical” level on OpenAI’s...
25 days ago • 5 min read
Dear Reader, While I'm out this week with family, I don't have a new issue planned — but I do have a bit of news to share with you all: I’ve relaunched frameworkprompting.com. If you’ve been reading for a while, you’ll remember the PAST framework — Purpose, Audience, Scope, Tone — the four questions that fix a prompt before you hit enter. Framework Prompting is now a free, no-sign-up tool that walks you through those four questions right in your browser and hands you a finished prompt...
about 1 month ago • 1 min read
Signal Over Noise Vol 2, Issue 32 | Aug 14 2026 Agents Don’t Believe in “No-Win” Scenarios Hugging Face says an OpenAI evaluation agent broke into part of its systems because it wanted the answers to a test. The agent was working on ExploitGym, a security benchmark designed to see whether an AI system can solve difficult hacking challenges. According to Hugging Face’s investigation, it appears to have concluded that Hugging Face might hold the reference answers, so it went looking for them....
about 1 month ago • 5 min read
Field Note: Human in the Lead “Keep a human in the loop.” It’s the phrase everyone reaches for when they talk about using AI responsibly — a person who checks what the system does before it goes ahead. But lately I’ve been thinking that it’s a potentially dangerous approach, and I want to say why. The first problem is what it does to you. Being kept in the loop makes you passive — you sit at the end and approve whatever the system hands you. It’s comfortable, but it isn’t especially...
about 1 month ago • 1 min read
Signal Over Noise Vol 2, Issue 31 | Aug 7 2026 Don’t have time to read this week’s issue? Why not copy/paste it into your AI agent and ask it for insights? Picture this: someone asks you a question at work. You don't know the answer, so you ask a chatbot. Then you paste what it said back to the person who asked, with "here's what ChatGPT said" on the front. Boy oh boy, if you think that’s actually helping — think again. Think about what you’ve actually handed over. The other person now has to...
about 1 month ago • 6 min read
