Latest posts
- GLM 5.2 and the coming AI margin collapse (part 1)Jul 06, 2026[email protected] (Martin Alderson)
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?Jun 22, 2026[email protected] (Martin Alderson)
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 developmentsJun 15, 2026[email protected] (Martin Alderson)
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 labJun 08, 2026[email protected] (Martin Alderson)
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?Jun 04, 2026[email protected] (Martin Alderson)
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 podcastJun 02, 2026[email protected] (Martin Alderson)
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?May 29, 2026[email protected] (Martin Alderson)
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 LambdaMay 14, 2026[email protected] (Martin Alderson)
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 problemMay 06, 2026[email protected] (Martin Alderson)
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 scenarioMay 04, 2026[email protected] (Martin Alderson)
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 DesignApr 19, 2026[email protected] (Martin Alderson)
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 routingApr 13, 2026[email protected] (Martin Alderson)
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?Apr 10, 2026[email protected] (Martin Alderson)
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?Apr 06, 2026[email protected] (Martin Alderson)
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 crisisMar 31, 2026[email protected] (Martin Alderson)
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 WindowsMar 17, 2026[email protected] (Martin Alderson)
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 dealMar 15, 2026[email protected] (Martin Alderson)
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 documentsMar 13, 2026[email protected] (Martin Alderson)
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 userMar 09, 2026[email protected] (Martin Alderson)
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?Mar 07, 2026[email protected] (Martin Alderson)
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 upMar 01, 2026[email protected] (Martin Alderson)
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 reviewsFeb 26, 2026[email protected] (Martin Alderson)
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?Feb 23, 2026[email protected] (Martin Alderson)
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?Feb 17, 2026[email protected] (Martin Alderson)
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 clonesFeb 13, 2026[email protected] (Martin Alderson)
I cloned Linear's UI and core functionality using Claude Code in about 20 prompts. Here's what that means for SaaS companies.
- How to generate good looking reports with Claude Code, Cowork or CodexFeb 08, 2026[email protected] (Martin Alderson)
A step-by-step guide to extracting your brand design system and generating on-brand PDF reports and slide decks using coding agents.
- Self-improving CLAUDE.md filesFeb 08, 2026[email protected] (Martin Alderson)
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.
- Wall Street just lost $285 billion because of 13 markdown filesFeb 05, 2026[email protected] (Martin Alderson)
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.Feb 01, 2026[email protected] (Martin Alderson)
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 TDDJan 25, 2026[email protected] (Martin Alderson)
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 thinkJan 19, 2026[email protected] (Martin Alderson)
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 CrunchJan 10, 2026[email protected] (Martin Alderson)
Why DRAM shortages, not capital, will define AI infrastructure growth through 2027
- Which programming languages are most token-efficient?Jan 08, 2026[email protected] (Martin Alderson)
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 minutesJan 05, 2026[email protected] (Martin Alderson)
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 agentsDec 29, 2025[email protected] (Martin Alderson)
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.Dec 27, 2025[email protected] (Martin Alderson)
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?Dec 22, 2025[email protected] (Martin Alderson)
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 itDec 18, 2025[email protected] (Martin Alderson)
Using ASTs and AI agents to reverse engineer minified JavaScript in minutes instead of weeks
- AI agents are starting to eat SaaSDec 15, 2025[email protected] (Martin Alderson)
Software ate the world. Agents are going to eat SaaS.
- Has the cost of building software just dropped 90%?Dec 08, 2025[email protected] (Martin Alderson)
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?Nov 30, 2025[email protected] (Martin Alderson)
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 IPv6Nov 25, 2025[email protected] (Martin Alderson)
Using IPv6 with Cloudflare to run multiple services on a single server without a reverse proxy
- How I use Claude Code to manage sysadmin tasksNov 16, 2025[email protected] (Martin Alderson)
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?Nov 02, 2025[email protected] (Martin Alderson)
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?Oct 25, 2025[email protected] (Martin Alderson)
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 hiredOct 17, 2025[email protected] (Martin Alderson)
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 GrowthOct 12, 2025[email protected] (Martin Alderson)
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 HeadedOct 02, 2025[email protected] (Martin Alderson)
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 cheaperSep 28, 2025[email protected] (Martin Alderson)
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 weeksSep 24, 2025[email protected] (Martin Alderson)
Google's Gemini AI Studio API has been suffering from severe reliability issues with little transparency about the problems on their status page.