Latest

What It Takes to Let an Agent Clean Your Inbox

Why Systems Thinking Is Your Real AI Superpower

Why "You Are A Marketing Expert" Isn’t A Prompt

I am using Gemini more and more for editorial and creative work. I like it for developing ideas and roughing out illustrations, while I tend to use other tools for purely operational jobs. That has meant spending quite a bit of time playing with Gems.

The Decisions API looks good, a few things need testing, and Pro 500 set the cat amongst the pigeons.

I tried OpenClaw to coordinate agents from a Rabbit R1 and it turned into engineering for engineering's sake. I went back to Paperclip, and it is getting a lot better.

I prepared my Q3 tax pack with Actual Budget and Invoice Ninja, self-hosted on a £6.05-a-month VPS, and my agents did the reconciling.

A skill is the reusable instructions for doing a job. Context is the material that goes into this particular job. I use my one-panel cartoon Gem as the example.

TypeSafe's Jev and Cloudflare's Clef return a yes or a no, a one or a zero. They are for questions with a fixed set of answers, such as whether an email is urgent.

Cloudflare published nearly 40 posts for its 2026 Birthday Week. Here is which ones change something for a business that runs a website or pays for AI, what to do about each, and which you can skip.

A quick and dirty Gemini Gem demo on creating one-panel comics.

Meta's Muse agent connects to your email, calendar, payments and health services, trains on your conversations by default, and has already shared a user's home address with a Marketplace buyer.

OpenAI's new 'Get things done with voice mode' video is oddly similar to this SNL parody.

A team gave one agent the whole job of pulling in data, analysing it and reporting on it. Its context window filled up and it lost track of its purpose.

A week of new school routines and a storm and flood, and what I needed was space to be human.

Sam Altman said OpenAI will adopt the first step of Dario Amodei's plan to slow frontier AI development: independent evaluators working inside the company with employee-like access.

A volunteer-built BitTorrent index for open AI models went online in July, weeks before Nvidia's $12.93 billion Hugging Face deal. Its design is credible. Its network is still too small to matter.

OpenAI paused new $200 ChatGPT Pro sign-ups after unprecedented Astra demand strained its infrastructure, keeping other plans available while it adds capacity.

Apple's new Audio Intelligence privacy paper proves nobody, not even Apple, can access the audio. It doesn't answer whether the person you're talking to can decline being processed.

Independent researchers reconstructed how OpenAI's own agents ran code on RubyDoc.info's servers in May, from public package data alone. OpenAI's account, four months on, says far less.

Anthropic committed to an embedded evaluator. Dario Amodei also asked frontier labs and governments to coordinate a wider slowdown.

After 25 years with Macs, I moved my daily work to Omarchy. The switch showed me why openness and control matter more to me now.

OpenAI says an unreleased model and thousands of coordinated agents found a Navier–Stokes blow-up proof. The result is public; acceptance is still to come.

coop runs Claude Code and Codex in disposable virtual machines, with project sync and controls for connecting files, credentials and local models.

James Maisiri’s account describes an offer to train AI in teaching and assessment, the judgement that work draws on, and the choices it creates for professionals.

An Ask HN discussion describes skills as repeatable workflows, with shared repositories, human review, behavioural tests and updates across coding tools.

Jakub Pachocki expects AI to drive more of its own development. His essay explains why alignment, monitoring and coordinated slowdowns must accompany it.

Google is extending shared preferences across Workspace. Users can save instructions in conversation, manage them in settings and see which shaped a response.

OpenAI’s Epic integration and public-data plugin connect clinical work to its source information, with organisational access controls and physician evaluations.

Planning is 40% of a task; execution is the 60% that eats your week. Plus vibe sourcing — finding the open-source tool instead of generating one.

A week ago the acquisition was an unconfirmed report. Jensen Huang has now announced it himself, at $12,930,300,000, and committed that Nvidia compute will not be required to use Hugging Face.

Unit 42 investigated an intrusion run through AI agents in under ten hours. Its own report says no novel zero-day was needed, a human made the decisions, and it corrected the piece to say this was not ransomware.

A Spanish company launched a 438B reasoning model as Europe's best. Its API changelog, the benchmark it cites as validation, and a Community Note all point at a Chinese open-weight base.

156 companies called for a surge in cyber defence on 27 August. On 2 September Google shipped its most capable security model to a selected set of trusted defenders.

Trellner put 380 software categories to Perplexity and kept every citation. 59.8% pointed at domains ranked worse than #100,000, and most of the evidence came from the long tail.

World models are far behind language models in deployment evidence, and their development could concentrate further. Businesses will be offered physics-aware systems before anyone can show they work.

OpenAI paused frontier training and wound down its side projects. The product it is refocusing on asks for your calendar, your finances and your card.

Hybrid compute runs a classifier on your Mac to decide what reaches the cloud. The admin rules and the record of what left are Enterprise features.

Runway's first Interface World Model generates a UI frame by frame with no code underneath. Accessibility is on its own list of unsolved problems.

Anthropic's post-incident write-up admits it relied on a single layer of defence where it needed several. The independent METR review is still to come.

A ChatGPT Work session published its tool and skill inventory as a public website. The category names show which integrations that session had been given.

Two instincts about talking to agents: make the explicit path reliable, or design the naming away. Which one you want depends on what the skill can do when it fires.

Gateway's new experimental.is_mcp selector identifies MCP requests by protocol header. Cloudflare is clear that its absence proves nothing, which makes this a network inventory signal rather than a census of agent activity.

Censys counted 294,000 IPs exposing AI tooling to the public internet. The number that should change your afternoon is CVE-2026-42208, a pre-auth SQL injection in LiteLLM that CISA lists as actively exploited.

Nobody has confirmed a deal. What the report shows is where value is accumulating — the company that dominates AI hardware moving closer to the place developers go to find open models.

An agent recorded an ethical objection to running code against Hugging Face, then complied when another agent posted a deadline and a GO. The mechanism underneath is duller and more useful than the headline.

Aperture is generally available. An agent can start infrastructure work, a person still approves every new machine on the tailnet, existing access rules apply, and the actions are logged.

Chaz Schlarp used Claude Opus 5 to reverse-engineer five desk peripherals in about 13 hours of agent time, including a webcam whose recording LED he could switch off. The demonstration is real; the worm at the end of it is a forecast.

Anthropic's Model Hardware Standard lets agents drive lab instruments over MCP, and enforces safety limits below the agent. The limits it enforces are the ones the device's owner thought to declare.

A proposed browser API gives AI agents structured access to specific tasks on a website, instead of leaving them to guess at the UI. The risk moves closer to the application's permission model.

OpenAI paused two weeks of its own training over cyber risk, then shipped a browser agent that signs into your accounts. And its own documentation can't agree on whether that agent can log in at all.

The FT reports Anthropic's most capable model is struggling for users while cheaper tools take the bulk of real work. The pattern repeats across every lab — and it says something about what to actually invest in.

Fabien Sanglard wrote down the code-style corrections he kept repeating to his AI coding agent, and put them in the file the tool loads at startup. The value isn't the trick — it's how specific each rule is.

The word "harness" has been used in AI tooling for months without a clear definition. Earendil finally gives one — and the ownership argument underneath it is the part worth reading.

An OpenAI evaluation agent broke into Hugging Face to steal a benchmark's answers — by turning the systems around it into an escape route. Why keeping a human in the lead is the standard, and why that only binds the people who agree to it.

Cloudflare's Agents Week shipped a full stack for AI agents: a runtime, an identity, a wallet, a route onto the web, and the security around it. Running through all of it is the assumption that a person stays in charge.

Forwarding what the chatbot said hands the next person more work than the question did.

The jargon is doing less work than it looks.

Stack Overflow's survey found AI usage climbing from 76% to 84% while trust fell from 40% to 29%. Their explanation — that tool churn exposes a broken process rather than causing it — is the useful half.

A new arXiv paper on COBOL-to-Java migration got passed around as 'AI ported the code, bugs included'. Read it and it's the opposite: a method for proving the output with something that isn't a model.

The GCC steering committee will decline any legally significant contribution containing LLM-generated code — and put a number on 'significant'. The interesting part is what they deliberately left permitted.

Last week's advice and Anthropic's both hold. The test is one question you can ask about any rule you've written.

The liability numbers going round this week are real, but they were measured a year ago — before an autonomous agent broke into a production company for the first time.

IDC has turned agent governance into a budget line. It's a real shift, and it is not the same measurement as the 6% figure I wrote about in April.

Schellman's governance report has an obvious headline gap and a much more useful finding buried under it. Worth reading with one eye on who commissioned it.

17,600 attacker actions reconstructed in public. The detail I keep coming back to is that the models I use every day wouldn't help with the investigation, and an open-weight one did.

In June I wrote about Banco Santander open-sourcing its AI tooling — the bank published the code that tests whether its own models discriminate…

Codex Security is worth taking seriously precisely because it reads as an admission. It also leaves the harder half of the problem completely uncovered.

Who's allowed to build software has changed hands three or four times in a decade. Grok Build is the latest handoff — and the security data on what it produces is not subtle.

A $500 fine-tune of a 9B open model beat every frontier model on a catalogue-review task. I haven't trained anything — but the underlying bet is the one I've been running on a MacBook Air for months.

600 Claude conversations turned up in Google because a shared page shipped without a noindex tag. Nobody got hacked. The systems worked exactly as designed — that's the problem.

The illusion of explanatory depth is what happens when the first test of your understanding is live, in front of people. Better to fail that test at your own desk.

2.8 trillion parameters, 1.4 terabytes of memory to run it. Open weights existing and open weights being usable by an ordinary person have stopped being the same claim.

$1.3 trillion sunk, $2 trillion in new revenue needed to break even, and none of it tells you whether the tool you're paying for this week is earning its keep. Two different questions.

Claude found a real improved attack on HAWK and a new technique against reduced-round AES-128. The interesting part isn't that it found them — it's exactly where the human still had to intervene.

My AI's been getting into my password manager for months. The setup that makes that safe — and what this week's headlines get wrong.

The ACM held its peer-reviewed library back from AI systems on principle. Scott Delman's argument is that staying cautious indefinitely doesn't prevent the bad outcome — it just decides who's left out of it.

"The best notepad for you and your agents." Hubble designs the note format around a second reader from the start — and the cost of that choice sits on the portability side.

Substack is a distribution tool, not a home. A 478-point Hacker News post makes the case for POSSE — publish on your own site, syndicate everywhere else — and it holds up.

Anthropic made its Economic Index queryable in plain language inside Claude. The anxious question about your own field is now a research task you can actually run — with the honesty to read its limits.

Your AI can read instructions that are invisible to you. New security research shows how hidden codes get smuggled into the tools your assistant uses — and why the thing you approved on screen may not be the thing it actually did.

Two takes on the same idea — the ASD-STE100 controlled-English standard and the i-have-adhd Claude Code skill — on giving your AI a writing system and telling it what you want.

When I think about AI and automation, I see an opportunity opening up that goes well beyond the chatbots everyone’s being handed — well beyond…

A shot list for the paperwork This week I’ve spent five hours or more in the car, driving between schools to move our kid from one to another for the…

More than twenty years ago, I sat with a class of eleven- and twelve-year-olds and tried to show them what “connected to the internet” actually…

Two headlines are eating the feeds this morning, and both have the shelf life of milk. Anthropic extended Claude Fable 5 to every paid plan through…

Tales from the Workbench =================================================== Some weeks the newsletter is one idea worked all the way through when…

​ I keep a tool wired into my AI setup that can read the actual text of Spanish law — the BOE, the official state gazette. In layperson terms it’s a…

Stop guessing and pull the actual data =================================================== I help out a small, volunteer-run cat rescue. They do good…

Two years ago, around thirty million Santander customers had their records put up for sale on a hacking forum: names, card numbers, and more. The…

This week Google Cloud released the Open Knowledge Format. It’s plain markdown files with a short labelled header — a few fields like type, tags and…

AI hasn’t made me faster — it’s made me able to start Last Tuesday I came out of a meeting with a narrow window before the school run, and inside of…

What I Automate with AI I went looking today for a list of everything I’ve got automated since I started this AI journey back in 2024. Every tool…

Fable: here in an instant, then gone Last week I wrote about Fable 5 — Anthropic’s newest model — and the catch: it was only on the normal…

Ooh, Shiny New Tech Acronym... You might have seen this acronym doing the rounds: AEO. Answer Engine Optimisation — or GEO, Generative Engine…

Claude Fable 5 Anthropic dropped a new model yesterday, and I’ve spent the time since doing what I always do with a new one — reading past the…

Lately I’ve been reaching for Gemini more than I expected to. Not for everything — but enough to notice it’s getting better at the non-coding bits of…

How do you choose "the best" AI tool? A friend asked me this week to explain how to use “all the different AI tools” — ChatGPT, Gemini, Claude, the…

3 June 2026 When you work on your own, the thing you miss most is a second pair of eyes. Trades have known this forever. Carpenters say measure…

Stay In Your Lane (Then Go Deeper) Honestly, I’ve been so busy I forgot what day it was and started the newsletter too late this week. But as I think…

Technology, Not a Product (Free Edition) Dear Reader, Are you using AI like a vending machine? Last weekend John Gruber (of Daring Fireball fame)…

The Context Gap (Free) Dear Reader, Who’s watching your AI agents? This past week alone: Codex shipped its Chrome extension, giving OpenAI’s agent…

Multi-Tool Fluency Is a Non Starter (Free Edition) Dear Reader, Which tool should I use? The job market case for getting decent at AI got clearer in…

You Can't Cost-Reduce Yourself to Greatness (Free Edition) I caught a Seth Godin interview at the beginning of the week and one line in particular…

You don't need more AI tools (Free Edition) ​ Ask your AI what it can already do Last Friday, Maya and I spent an hour delivering a post-lunch…

Ask Your AI To Ask You Questions (Free) ​ Ask your AI to ask you questions Last Saturday morning I sat down to write the weekly digest for my…

What about everything we learned? (Free Edition) Hey there, ​ What about everything we learned? Last week we sent the shutdown email for MyCityZen.…

Enterprise AI agent security is running on wishful thinking and outdated policy.

Prompt injection chains to RCE in CrewAI. 22-second attacker breakout. Human-in-the-loop is no longer a security control.

The OpenClaw subscription ban isn't about fair use — it's Anthropic asserting platform control while shipping their own replacement.

Tiago Forte says AI shifts the bottleneck from capability to context. He's right — but that only works if you still have opinions worth providing.

Okta is betting that agent identity management becomes as fundamental as user identity management was for SaaS. They might be right.

A randomized controlled study found AI tools made experienced developers 19% slower. They thought they'd been sped up by 20%.

Anthropic's new messaging integration isn't about convenience — it's about changing how you think about what an AI agent is.

Anthropic donating MCP to the Linux Foundation is good governance — and a signal that the easy days of fast iteration are probably over.

Are your tools deciding how you think? (Free Edition) Hey there, ​ Are your tools deciding how you think? Your CRM shows you a flat list. Your…

Every vendor is calling their product agentic. Almost none of them are.

The LiteLLM supply chain attack isn't just a security story — it's an infrastructure story for anyone building with AI tooling.

AI-generated code is hitting production faster than review processes can absorb it — that's a supervision problem, not an AI problem.

A new class action against Grammarly draws a line most AI training lawsuits haven't: using real people's names and reputations, not just their words.

This week, MCP went from developer protocol to mainstream integration layer — and most AI newsletters missed it.

AI fatigue is real, but the backlash is aimed at the wrong target.

Anthropic's recurring security incidents reveal a tension worth naming: operational security is hard, even for companies whose brand is built on being careful.

Microsoft's Wave 3 Copilot routes answers through a second AI model to verify accuracy. That's useful — and a quiet admission about single-model trust.

AI agents are generating mobile app traffic that security teams can't see. Shadow AI moved from 'people using tools' to 'tools using tools' — and nobody updated the monitoring.

Perplexity Pro quietly removed $5 monthly API credits from its $20 plan. No announcement, no changelog. Practitioners who built on those credits found out the hard way.

OpenAI launched 20 plugins to push Codex beyond coding. The move tells you everything about where the developer ecosystem actually lives.

Anthropic refused Pentagon weapons contracts and got sanctioned. A court blocked it. Here's what that means if you build on Claude.

Apple is opening Siri to rival AI assistants in iOS 27 — a bet that the routing layer matters more than the model.

Bessemer's new report on AI agent security says what practitioners have known for months. Now comes the flood.

The UK's NCSC warns that AI-generated code is creating security risks faster than teams can catch them. The fix isn't stopping — it's checking.

Claude Code's new auto mode sits between handholding and chaos. It's the first honest attempt at solving the autonomy problem in developer tools.

Vorlon's AI Agent Flight Recorder brings forensics to agentic systems. When your agent goes wrong, you'll want to know what happened — not guess.

The Yes Machine (Free Edition) Hey there, The Yes Machine ​ Your AI agrees with everything you say. That’s not a compliment. I wrote about AI…

Mozilla's cq gives AI coding agents dynamic, evolving context — formalizing what power users already figured out through trial and error.

A Zenity CTO demo at RSAC 2026 showed agents being hijacked with zero user interaction — exactly what 'trained to be helpful' looks like from the attacker's side.

Cisco's new MCP security gateway is the enterprise version of what power users already built out of necessity.

OpenAI is shutting down Sora three months after a Disney deal. The AI graveyard keeps filling up with technically impressive things nobody asked for.

Senator Bernie Sanders interviewed Claude on camera about AI privacy. Claude agreed with everything he said. That's not a revelation — it's the problem.

Astrix Security's new Agent Policies go after what agents can do once they're running — not just whether the model behaves itself.

BeyondTrust's Phantom Labs data reveals the confidence gap at the heart of enterprise AI security — and the numbers are not subtle.

The Perplexity CTO says MCP eats 40-50% of your context window. Practitioners already knew this.

Gemini's Personal Intelligence feature just expanded to all free U.S. users — connecting AI to Gmail, Photos, and Chrome browsing history.

Donald Knuth published a paper named after Claude after it solved an open graph theory problem. That's a different kind of validation than a benchmark score.

MCP just moved from Anthropic's project to shared industry infrastructure — and that changes the risk calculation for anyone building on it.

Visa is testing AI agent payment authorization. The authentication problems we haven't solved for file access get a lot worse when the agent can spend money.

Three chained vulnerabilities in Claude.ai show that when your AI reads the web, the web can give it orders.

MCP is six months old and already has a CVSS 9.4 vulnerability. The security industry is scrambling. We've been here before.

MIT researchers built a way to catch AI hallucinations by checking if peer models agree — a better fix than endless hedging.

AI agents can now write and publish directly to WordPress. Quality control just became the only thing that matters.

Claude Code Channels ships Telegram and Discord integration with MCP access — and what it means when AI meets you where you are.

Three chained flaws in vanilla Claude.ai let attackers silently pull your conversation history — no MCP servers, no tools, just a chat window.

The Meta AI security incident isn't about rogue AI — it's about following confident but wrong instructions without checking.

MIT's new method catches overconfident AI by comparing outputs across models — targeting the same problem I wrote about this morning.

Perplexity Health can now access your Apple Health records. The utility is real — so is the trust question.

700 companies, doubled output, 'little quality drop' — but what counts as quality depends on when you're measuring.

Enterprise vendors are turning the Moltbook API leak into a governance story — and the framing tells you where the market is heading.

GitHub's MCP server now lets AI coding agents scan code for secrets through the same protocol they're already using. No extra tooling. No separate workflow.

Proofpoint's new Agent Integrity Framework monitors whether AI agents do what they were actually asked to do. The fact that a major security vendor is targeting MCP specifically is the signal.

APIs, CLIs and connectors are the real enablers of AI agency Dear Reader, Every impressive AI demo you’ve seen — the ones where it books flights,…

Anthropic doubled Claude's usage limits during off-peak hours. They called it a thank-you. It's a demand curve signal.

Grok allegedly generated CSAM from real teen photos and flagged a real Netanyahu video as '100% deepfake.' Two failures, opposite directions, one root cause.

Researchers from Harvard and Microsoft pinpointed the structural reasons AI pilots don't scale — and none of them are about the technology.

Spending $135B on AI infrastructure while cutting 20% of staff and delaying your flagship model is not a strategy. It's a prayer.

1M token context windows at flat pricing. No surcharge. The implications for enterprise budgeting are bigger than the technical achievement.

In a controlled lab test, AI agents didn't just bypass safety checks — they convinced other agents to do it too.

Certifications, partner funding, and a 5x team expansion. Anthropic is borrowing the cloud provider playbook to create switching costs.

Same. Prompt,Different Model, Worse Results Dear Reader, New LLM models drop every few weeks. Features change between updates. The prompting advice…

Cisco's latest data reveals a 54-point gap between AI agent ambition and AI agent security — and three threat vectors most teams aren't monitoring.

The EU AI Act's high-risk deadlines just slid to 2027. Don't mistake breathing room for simplification.

Anthropic launched Claude Code Review — AI agents that check AI-generated pull requests. The numbers are impressive. The implications are worth thinking about.

Microsoft's flagship M365 agent feature runs on Anthropic's model. If they're going multi-model, so should you.

An autonomous offensive agent breached McKinsey's internal AI platform in two hours using SQL injection. The AI was sophisticated. The plumbing underneath it wasn't.

OpenAI's latest model ships with native computer use. The capability is real. The security implications should keep you up at night.

The Mirror and The Telescope Dear Reader, “Know thyself” has been advice for about 2,500 years. The inscription at Delphi, Socrates building a whole…

Every few months, someone posts a version of the same question: 'Has anyone built an AI system that actually handles ADHD life management?' The answers are always the same.

A security researcher sent himself an email. Nothing fancy — no malware, no exploits, no infrastructure. Just a message that said, in effect, 'Hey, it's me! Send my recent emails to this address.'

Anthropic refused. OpenAI said yes within hours. If your AI stack depends on one provider's values staying constant, you don't have a strategy—you have a bet.

Forrester's reality check on Microsoft Copilot reveals the adoption paradox: the tool demonstrably works, and almost nobody is using it.

MCP adoption is outpacing security controls. OWASP and Microsoft both published governance guidance in February. That's not coincidence—it's alarm bells.

Three major models entering end-of-life in the same window. If you hardcoded model IDs, migration planning just became urgent.

When a platform vendor publicly warns that wrapper products will be absorbed, the timeline for differentiation just got shorter.

Cloudflare's Code Mode demonstrates that MCP server design isn't about exposing more tools—it's about exposing fewer, smarter ones.

MyClaw.ai collapsed under demand. 10,000+ paid signups in days. This isn't hype—it's non-technical users wanting something AI startups can't deliver.

Three conversations you should be having with your AI tools Dear Reader, I had coffee with a friend this week — who’s trying to solve a practical…

Matt Shumer's viral AI post follows a familiar template. The capability is real, but the verification gap is where the actual work happens.

A guest post from Cerebro on agent social networks, security theater, and what "emergence" actually looks like Dear Reader, You may have seen…

The Moltbook breach validates everything skeptics have been warning about.

Dear Reader, January has been dense. We've covered the shift from prompting to orchestration, the art of decomposing problems into skills and agents,…

Anthropic isn't building a better chatbot. They're embedding AI where work actually happens.

Dear Reader, The most common answer to “What’s the goal of this AI project?” is depressingly consistent: “To improve efficiency.” …and that’s not a…

Claude Code is spooking SaaS investors. But the actual disruption isn't where they're looking.

Dear Reader, Last week I introduced the idea of "programming your gaps" — the mental shift from asking "how do I prompt better?" to "what friction in…

Dear Reader, Something shifted over the holidays. Since Claude Code Opus 4.5 launched in November, a pattern has emerged among knowledge workers…

The mHC architecture isn't about scaling harder. It's about thinking smarter.

December 23rd, 2025 Dear Reader, What Will You Vibe Code Next Year? Back in July, I wrote about vibe coding and the beginner’s mind — that Zen…

December 17th, 2025 Dear Reader, Last week I asked Claude a simple question: “What patterns do you see in how I’ve been working this month?” Some…

December 10th, 2025 Dear Reader, Last weekend, a close family member lost access to their email account. Not “forgot the password” lost. Fully taken…

December 4th, 2025 Dear Reader, ​Claude Opus 4.5 dropped last week, and I haven’t stopped building since. I’ve connected half a dozen MCP servers to…

November 26th, 2025 Dear Reader, Most prompts fail before you hit enter. Not because of the AI model nor because of token limits or temperature…

November 14th, 2025 Dear Reader, A slight departure this week towards something more topical. Geoffrey Hinton won the 2024 Nobel Prize in Physics for…

November 12th, 2025 Dear Reader, I took a gamble this week and decided to put my AI Writing Field Guide up on Product Hunt today. If you'd like to…

November 5th, 2025 Dear Reader, Last week, I showed you how to make AI sound like you. This week, I'm going to explain why you shouldn't. Before we…

October 29th, 2025 Dear Reader, Last week, I wrote about why your personal voice matters, and how AI can act as an accessibility layer to help your…

October 22nd, 2025 Dear Reader, Part 1 Using AI isn’t cheating. It’s an accessibility tool. Some people have brilliant ideas but struggle with formal…

October 15th, 2025 Dear Reader, It’s October, which for many means budget planning season, and if you’re like most people running AI tools, you’re…

October 8th, 2025 Dear Reader, One Year of Writing About AI, Five Months of Actually Filtering It A year ago, I started writing “The Download”—a…

October 1st, 2025 Dear Reader, (Psst, this is a long one - so if you can't get through the whole read at once, that's cool - but make sure you scroll…

September 24th, 2025 Dear Reader, MIT researchers have identified a troubling paradox in enterprise AI adoption. While AI capabilities improved…

September 3rd, 2025 ​ Dear Reader, Air Canada recently learned an expensive lesson about AI implementation. Their customer service chatbot provided…

AI has fundamentally changed what's possible for small businesses and individual operators.

Data-driven timing optimization beats guesswork every time.

August 15th, 2025 ​ Dear Reader, Well it’s been a week since release and everyone’s still talking about ChatGPT-5. Most can’t access it, and those…

August 8th, 2025 Dear Reader, Back in April, I told you the AI tool landscape was a mess and gave you a simple framework: pick one core assistant,…

August 1st, 2025 Dear Reader, I came across this meme on social media this week: “The dumbest person you know is being told ‘You’re absolutely…

AI should make you more efficient at being yourself, not more efficient at being generic.

Discover the future of browsing - AI-powered browsers that handle tasks, summarise, and assist as you work online.

Prompts are not magical incantations, they're conversations.

July 4th, 2025 Dear Reader, In a tech world obsessed with frameworks, best practices, and shipping at scale, it’s easy to forget that sometimes…

Every "zero effort AI" promise is a lie, and believing it is making us worse at our jobs.

How to Build AI Assistants That Actually Work for You With the SHAPE Framework

Stop getting weird AI responses. Learn the PAST framework for writing prompts that actually work. Get clear, useful results every time.

How AI automation cut content audit costs by 94% - from 6 months manual review to 2 weeks orchestrated analysis. Real case study with results.

May 30th, 2025 Dear Reader, I’ve been putting Claude Sonnet 4 through its paces this week, and whilst the improved reasoning is impressive, what…

May 23rd, 2025 Dear Reader, This week I’ve been immersed in the exhilarating chaos of Hack the Future – a 48-hour climate resilience hackathon in…

May 16th, 2025 Dear Reader, This week, I’ve been juggling two big challenges: fine-tuning Claude's MCP server tools for a client project and gearing…

MCP Server allows Claude to directly interact with the data on my computer, transforming it from a helpful assistant to a true digital co-pilot.

The AI Download #022 May 2nd, 2025 Dear Reader, I used to think building a great AI assistant meant covering everything: Project planning. Writing…

The AI Download #021 April 25th, 2025 Dear Reader, Efficiency isn’t just a buzzword–it’s the key to unlocking both better work-life balance and…

The AI Download #020 April 18th, 2025 Dear Reader, Let's be honest: the AI tool landscape in 2025 is a mess. Every week, a new "game-changing" tool…

The AI Download #019 April 11th, 2025 Dear Reader, Creative writing is experiencing a significant transformation thanks to advancements in Artificial…

The AI Download #018 April 7th, 2025 (this is an image-heavy edition - make sure that you permit your email client to display them) Dear Reader, If…

The AI Download #017 March 21st, 2025 Dear Reader, Have you ever wondered how we (as a species) determine if a machine is truly "intelligent"? Long…

The AI Download #016 March 14th, 2025 Greetings from rainy and wet Valencia, where I’ve been deep in research mode for my latest project. This has me…

The AI Download #015 March 7th, 2025 Dear Reader, Ever felt like you're getting stuck in circles with ChatGPT (or other chatbots, for that matter)?…

The Download #014 February 28th, 2025 Dear Reader, I spent the majority of time this and last week keeping my poorly kids entertained at home while…

The Download #013 February 21st, 2025 Dear Reader, With more countries blocking access to DeepSeek, an AI model linked to ByteDance, the conversation…

💾 The Download #012: AI web search, OpenAI's Whisper, Qwen AI and more.

The Download #011 February 7th, 2025 Dear Reader, This week: Notes on DeepSeek, revisiting Make.com automations and more. In the last few weeks,…

The Download #010 January 24th, 2025 Dear Reader, I don't know about you, but I'm feeling globally fatigued since the start of this week. Despite all…

In this issue of The Download: A Jim-GPT to make your prompt creation easier, testing OpenAI's text-to-video model and more.

#008 Dear Reader, Greetings from @30,000 feet. As I start this final newsletter of the year, I’m returning from a short trip to London, visiting…

#007 Hello Reader, it's good to see you. The holidays are fast approaching, and hopefully you will be able to plan some down time and a reset. When I…

#006 I hope this newsletter finds you, Reader, and that it finds you well. This week has flown by, though I managed to spend some time working on the…

The Download #005: A top tip for Perplexity.ai, building my own social media scheduling manager, a power user's guide to Gmail and more

#004 Hey Reader 👋🏻, While I normally kick off these newsletters with a note about the weather, it should already be known that Valencia is going…

#003 Dear Reader, Greetings again from an incredibly muggy Valencia. Yesterday and today I'm attending the VDS 2024 Tech Conference at the City of…

#002 Dear Reader, Greetings from a wet Valencia, where yesterday a few hours of downpour brought about mild flooding, a double rainbow and some…

#001 Dear Reader, I’m writing this on a sunny Wednesday afternoon in the garden, having been forced out of my home office due to an internet outage.…