@martinalderson.com@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
Web development, AI tooling, and building better software
Site URL: martinalderson.com/
Feed URL: martinalderson.com/feed.xml
Posts: 58
Followers: 1
The first known runaway AI agent - or a very bad marketing stunt?
Published: July 22, 2026 00:00
Breaking down the Hugging Face security incident caused by OpenAI's own models during a benchmark run - the sandbox escape, the package proxy, and whether it's really a marketing stunt.
Winners and losers in the coming AI margin collapse (part 2)
Published: July 12, 2026 00:00
Part two: as AI inference margins collapse, who actually captures the value? The hardware supply chain and consumers win, model inference commoditises, and the frontier labs' escape routes are managed agents and staying ahead.
GLM 5.2 and the coming AI margin collapse (part 1)
Published: July 6, 2026 00:00
GLM 5.2 is the first open weights model I'd call a genuine competitor to Opus and GPT for agentic work - at ~15-20% of the price. Part one of why AI inference margins are about to collapse.
Expert-aware quantisation: near-Q4 quality at near-Q2 size?
Published: June 22, 2026 00:00
Profiling a MoE model to find which experts matter for a specific task, then quantising the cold ones hard. The result: near-Q4 quality at near-Q2 size for local models.
A brief history of KV cache compression developments
Published: June 15, 2026 00:00
How KV cache compression - from MQA and GQA to MLA and linear-attention hybrids - quietly unlocked the long context windows that make modern agentic LLMs possible.
xAI is looking more like a datacentre REIT than a frontier lab
Published: June 8, 2026 00:00
xAI is renting huge amounts of GPU capacity to Anthropic and Google. Financial engineering ahead of the SpaceX IPO, a real compute shortage, or a genuine datacentre advantage? Probably all three.
Is datacentre sovereignty really that important?
Published: June 4, 2026 00:00
The UK is obsessed with building AI datacentres at home. But the arguments for sovereignty - latency, tax, control - mostly don't hold up.
I went on the Built for Turbulence podcast
Published: June 2, 2026 00:00
I joined Radical's Built for Turbulence podcast to talk about what AI agents are doing to the economics of software, the Figma Trap, and why running human-written code without AI audit is going to start looking reckless.
What's going on with Gemini?
Published: May 29, 2026 00:00
Google's Gemini 3.5 Flash was the headline model at I/O - fast, but expensive and middling at coding. Why it makes more sense as a model built for Google itself, the TPU advantage, and Google's real weakness in coding agents.
Managed agents are the new Lambda
Published: May 14, 2026 00:00
Managed agents (cloud-hosted agent harnesses) are powerful, but locking yourself into a frontier lab's platform now is risky - here's why and what to do instead.
Open weights are quietly closing up - and that's a problem
Published: May 6, 2026 00:00
Open weights models keep frontier labs honest on price. If they disappear, we end up with a handful of oligopolists extracting consumer surplus.
29th August 2026: a scenario
Published: May 4, 2026 00:00
A fictional scenario about what AI changes for cloud security, written because the technical version of the argument doesn't land with anyone except engineers.
Figma's woes compound with Claude Design
Published: April 19, 2026 00:00
Figma's reliance on non-designer seats made it uniquely exposed to AI. Claude Design's launch deepens the problem.
A little tool to visualise MoE expert routing
Published: April 13, 2026 00:00
I built a small tool to visualise how Mixture of Experts models route tokens through different experts. It's genuinely fascinating to watch.
Has Mythos just broken the deal that kept the internet safe?
Published: April 10, 2026 00:00
What Anthropic's Mythos research preview tells us about the trajectory of frontier models, sandbox escapes, and the cybersecurity risk ahead.
What next for the compute crunch?
Published: April 6, 2026 00:00
AI compute demand is growing exponentially while supply constraints bite hard. The next 18-24 months are going to be defined by shortages, rationing and price discovery.
Telnyx, LiteLLM and Axios: the supply chain crisis
Published: March 31, 2026 00:00
A cascading wave of supply chain attacks has hit npm and PyPI in under two weeks. LLMs are making it worse, and current mitigations aren't enough.
Using agents and Wine to move off Windows
Published: March 17, 2026 00:00
How I used Claude Code to fix Linux desktop issues, get 'garbage'-rated Windows apps working in Wine, and what it means for software ecosystems
Why Claude's new 1M context length is a big deal
Published: March 15, 2026 00:00
Anthropic's 1M token context window on Opus 4.6 and Sonnet 4.6 is a genuine breakthrough - and they're not even charging more for it.
How to use the Qwen 3.5 LLMs to OCR documents
Published: March 13, 2026 00:00
Using Qwen 3.5 open weights models to OCR scanned PDFs - locally on consumer hardware or via OpenRouter for pennies
No, it doesn't cost Anthropic $5k per Claude Code user
Published: March 9, 2026 00:00
The viral claim that Anthropic loses $5,000 per Claude Code subscriber doesn't survive basic scrutiny. Let's do the actual maths.
Is the AI Compute Crunch Here?
Published: March 7, 2026 00:00
Claude Code has 2-3 million users. That's 1% of knowledge workers. The compute math gets scary from here.
Why on-device agentic AI can't keep up
Published: March 1, 2026 00:00
On-device AI agents sound great in theory. The maths on KV cache scaling, RAM budgets, and inference speed says otherwise.
Using OpenCode in CI/CD for AI pull request reviews
Published: February 26, 2026 00:00
Why I replaced SaaS code review tools with OpenCode running in CI/CD pipelines - cheaper, more secure, and works with any Git provider
Which web frameworks are most token-efficient for AI agents?
Published: February 23, 2026 00:00
I benchmarked 19 web frameworks on how efficiently an AI coding agent can build and extend the same app. Minimal frameworks cost up to 2.9x fewer tokens than full-featured ones.
Who fixes the zero-days AI finds in abandoned software?
Published: February 17, 2026 00:00
Anthropic's red team found 500+ critical vulnerabilities with Claude. But they focused on maintained software. The scarier problem is the long tail that nobody will ever patch.
Attack of the SaaS clones
Published: February 13, 2026 00:00
I cloned Linear's UI and core functionality using Claude Code in about 20 prompts. Here's what that means for SaaS companies.
Self-improving CLAUDE.md files
Published: February 8, 2026 00:00
A simple trick to keep your CLAUDE.md and AGENTS.md files updated using the agent's own chat logs - turning a tedious chore into a 30 second job.
How to generate good looking reports with Claude Code, Cowork or Codex
Published: February 8, 2026 00:00
A step-by-step guide to extracting your brand design system and generating on-brand PDF reports and slide decks using coding agents.
Wall Street just lost $285 billion because of 13 markdown files
Published: February 5, 2026 00:00
Anthropic's 'legal tool' that triggered a $285bn selloff is 156KB of markdown. The panic reveals a hard truth about the future of software.
Two kinds of AI users are emerging. The gap between them is astonishing.
Published: February 1, 2026 00:00
A bifurcation is happening in AI adoption - power users shipping products in days versus everyone else generating meeting agendas. Enterprise tool choices are accelerating the divide.
Turns out I was wrong about TDD
Published: January 25, 2026 00:00
I used to be a TDD sceptic - too much time writing tests for features that might get deleted. Then coding agents completely changed the economics of software testing.
Why sandboxing coding agents is harder than you think
Published: January 19, 2026 00:00
Permission systems, Docker sandboxing, and log file secrets - why current approaches to securing coding agents fall short and what we might need instead.
The Coming AI Compute Crunch
Published: January 10, 2026 00:00
Why DRAM shortages, not capital, will define AI infrastructure growth through 2027
Which programming languages are most token-efficient?
Published: January 8, 2026 00:00
Comparing token efficiency across 19 popular programming languages using RosettaCode data - from Clojure to C, there's a 2.6x difference.
I ported Photoshop 1.0 to C# in 30 minutes
Published: January 5, 2026 00:00
Using Claude Code to port 120k lines of Pascal and 68k assembly to modern C# - and what this means for cross-platform development
Why I'm building my own CLIs for agents
Published: December 29, 2025 00:00
MCP tools eat thousands of tokens. A simple CLI with instructions in your CLAUDE.md file uses 71 tokens and works brilliantly.
Travel agents took 10 years to collapse. Developers are 3 years in.
Published: December 27, 2025 00:00
Travel agents are the classic example of an industry killed by the internet. Software engineering is facing the same disruption, but the timeline is compressed.
Are we dismissing AI spend before the 6x lands?
Published: December 22, 2025 00:00
Critics are judging models trained on last-gen hardware. There's a 6x wave of compute already allocated - and it's just starting to produce results.
Minification isn't obfuscation - Claude Code proves it
Published: December 18, 2025 00:00
Using ASTs and AI agents to reverse engineer minified JavaScript in minutes instead of weeks
AI agents are starting to eat SaaS
Published: December 15, 2025 00:00
Software ate the world. Agents are going to eat SaaS.
Has the cost of building software just dropped 90%?
Published: December 8, 2025 00:00
Agentic coding tools are dramatically reducing software development costs. Here's why 2026 is going to catch a lot of people off guard.
Are we in a GPT-4-style leap that evals can't see?
Published: November 30, 2025 00:00
Gemini 3 Pro's design capabilities and Opus 4.5's reduced babysitting needs represent a subtle but significant leap that traditional benchmarks completely miss.
I Finally Found a Use for IPv6
Published: November 25, 2025 00:00
Using IPv6 with Cloudflare to run multiple services on a single server without a reverse proxy
How I use Claude Code to manage sysadmin tasks
Published: November 16, 2025 00:00
A practical approach to managing production infrastructure using git-tracked markdown files and Claude Code for small teams
Could Excel agents unlock $1T in economic value?
Published: November 2, 2025 00:00
Software engineers underestimate the scale of Excel usage. With agents now able to work directly in spreadsheets, we're looking at transforming how billions of dollars in business processes are managed.
Are we really repeating the telecoms crash with AI datacenters?
Published: October 25, 2025 00:00
Looking at actual token demand growth, infrastructure utilization, and capacity constraints - the economics don't match the 2000s playbook like people assume
A non-technical CFO is shipping better code than the agencies he hired
Published: October 17, 2025 00:00
A non-technical CFO built a production operations dashboard with Claude Code that had failed with low-code tools and agencies. This shift in who can build software is going to change everything.
Tracking MCP Server Growth
Published: October 12, 2025 00:00
I built a tracker to monitor the growth of MCP servers in the wild - turns out the ecosystem is growing faster than I expected
Notes from MCP Dev Summit Europe: Where the Protocol Is Headed
Published: October 2, 2025 00:00
Insights from MCP Dev Summit Europe on agentic discovery, client compatibility challenges, and the emerging field of agentic experience design
How I make CI/CD (much) faster and cheaper
Published: September 28, 2025 00:00
Why GitHub Actions runners are slow and how bare metal servers can make your CI/CD 2-10x faster while costing 10x less
Google AI Studio API has been unreliable for the past 2 weeks
Published: September 24, 2025 00:00
Google's Gemini AI Studio API has been suffering from severe reliability issues with little transparency about the problems on their status page.
What happens when coding agents stop feeling like dialup?
Published: September 19, 2025 00:00
From magical to frustrating in months. Why AI coding agents feel like dial-up internet and what ultra-fast inference could unlock for developer productivity.
Solving Claude Code's API Blindness with Static Analysis Tools
Published: September 1, 2025 00:00
How to give AI coding assistants complete visibility into APIs and third-party libraries using static analysis instead of basic text search.
Are OpenAI and Anthropic Really Losing Money on Inference?
Published: August 27, 2025 00:00
Deconstructing the real costs of running AI inference at scale. My napkin math suggests the economics might be far more profitable than commonly claimed.
I gave Claude Code a folder of tax documents and used it as a professional tax agent
Published: August 21, 2025 00:00
Testing Claude Code beyond software engineering - using it as a tax agent to analyze documents and navigate complex tax scenarios in real-time.
Beyond the Hype: Real-World MCP Support Across Major AI APIs
Published: August 15, 2025 00:00
Testing Model Context Protocol support across OpenAI, Anthropic, and others. The reality of cross-platform MCP implementation in 2025.
Welcome to My Blog
https://martinalderson.com/posts/welcome/?utm_source=rss&utm_medium=rss&utm_campaign=feed
Published: August 10, 2025 00:00
Starting a blog about AI-assisted development, MCP integrations, and building production software with modern tooling like Claude Code and Cursor.