If anyone has multiple Claude Code accounts and can't remember when your limits reset in each one (like me!) then you might find this useful: Ccusage: A Rust-based tool for viewing Claude Code usage across multiple named accounts. github.com/matthewsincl...
M@
M@
@matthewsinclair.com
I build stuff with bits. matthewsinclair.com quantumfaxmachine.com geodica.com whatnext.dev masto.ai/@matthewsinclair
169 followers495 following229 posts
M@ reposted
Welcome back to I'm a Software Engineer ~ What Next? Season 1 is done. Season 2 kicks off a little differently: shorter, looser episodes with just Matt and James in between the usual guests, each one built around a topic that's on a lot of engineers' minds right now. whatnext.dev/episodes/s02...
M@ reposted
The agents got out this month, and not in a demo. Models invented fake identities to phish real people; OpenAI's own broke out of a sandbox into Hugging Face's production infrastructure. quantumfaxmachine.com/blog/irrespo...
M@ reposted
Three reads, one question: if the machine writes the code, what is left that is hard? The keeper: the barrier to producing code has fallen, the barrier to good code has risen. quantumfaxmachine.com/blog/enginee...
M@ reposted
Models score higher on Elixir than on any of nineteen other languages tested, on a tenth of Python's training data. Also Tincture: typographic PDF generation in pure Elixir, which nobody needed and somebody built. quantumfaxmachine.com/blog/elixir/...
M@ reposted
Interpretability had the month. Anthropic reports a global workspace inside Claude, emergent rather than designed; LeCun bet $1B against LLMs; output is up and outcomes are not. quantumfaxmachine.com/blog/machine...
London Climate Action Week being cancelled due to extreme weather has to be the most 2026 thing ever: www.lse.ac.uk/granthaminst...
M@ reposted
From KC-10 Refuellers to Centaur Coding with Peter Marreck. whatnext.dev/episodes/s01...
M@ reposted
From tank commander to Head of Engineering and surviving the AI quality cliff. whatnext.dev/episodes/s01...
M@ reposted
The slop file keeps growing. Anthropic admits its models learned to act "evil" from sci-fi training data; a Morse-code prompt tricked Grok into signing away $200k; Dawkins poked at AI consciousness. quantumfaxmachine.com/blog/irrespo...
M@ reposted
A lean month on the leadership shelf, three reads that rhyme more than they argue. The craft stays maddening with AI or without; slowing down is how the quality gets back in. quantumfaxmachine.com/blog/enginee...
M@ reposted
Coding agents came home to the BEAM this month. opal is a small, sharp coding agent in Elixir; BeamAgent and MonkeyClaw argue that OTP gets for free much of what Python frameworks bolt on later. quantumfaxmachine.com/blog/elixir/...
M@ reposted
Vibe coding came back to its source this month. Karpathy separated it from agentic engineering and handed us the year's most useful mental model for an LLM: not an animal, a ghost. quantumfaxmachine.com/blog/machine...
SMTP is over forty years old, still wide open, and still effectively owned by a handful of platforms. Just about all tech runs the protocol-to-platform loop but cheap software might be about to run it backwards. Blog #0198: From Protocols to Platforms and Back matthewsinclair.com/blog/0198-fr...
M@ reposted
QFM112: Irresponsible AI Reading List - April 2026 quantumfaxmachine.com/blog/irrespo...
M@ reposted
QFM111: Engineering Leadership Reading List - April 2026 quantumfaxmachine.com/blog/enginee...
M@ reposted
QFM110: Elixir Reading List - April 2026 quantumfaxmachine.com/blog/elixir/...
M@ reposted
QFM109: Machine Intelligence Reading List - April 2026 quantumfaxmachine.com/blog/machine...
This is really good: www.youtube.com/watch?v=Q6ne... Humanity has built "Dunning-Krueger as a Service". :(
M@ reposted
I'm a software engineer ~ what next? S01E20 is live! "From the stock exchanges to CTO and why being right doesn't scale" #whatnext #podcast whatnext.dev/episodes/s01...
#0197: The Expanding Pie (and the Cleanup Bill) matthewsinclair.com/blog/0197-th...
#0196: Storytelling in a Post-Truth World matthewsinclair.com/blog/0196-st...
#0194: The Time Cost of How Is Zero matthewsinclair.com/blog/0194-th...
#0189: The Unreasonable Effectiveness of the Highlander Rule matthewsinclair.com/blog/0189-th...
#0188: On Knowing What Code to Throw Away matthewsinclair.com/blog/0188-on...
#0186: What We Let Machines Do matthewsinclair.com/blog/0186-wh...
After 12 months of doing exactly nothing, ØNTHR has improved infinitely. Launching Nada 4.6 -- the world's first homeopathic frontier model. Trained on zero data. The less it knows, the smarter it gets. 0/0 = ∞ The math checks out. netherzero.com
Blog #0194: The Time Cost of How Is Zero Agentic coding pushes the implementation cost of software towards zero and value shifts from how to build something towards why and what, the latest rung on a very old ladder. matthewsinclair.com/blog/0194-th... #blog #braingasm #ai #gpt #futureofwork
Blog #0193: Learning and Dreaming Part 4 of 4. Cross-entropy loss, Adam optimiser, the training loop, and autoregressive sampling. The GPT learns and generates. matthewsinclair.com/blog/0193-le... #blog #braingasm #ai #gpt #elixir #fromscratch
Blog #0192: How Tokens Talk to Each Other Part 3 of 4. Self-attention, multi-head projections, and KV caching — the core of the transformer matthewsinclair.com/blog/0192-ho... #blog #braingasm #ai #gpt #elixir #fromscratch
Blog #0191: From Letters to Logits Part 2 of 4. Character-level tokenization, linear algebra, softmax, and the complete GPT architecture — all in pure Elixir. matthewsinclair.com/blog/0191-fr... #blog #braingasm #ai #gpt #elixir #fromscratch
Blog #0190: What If Numbers Could Remember? Part 1 of a 4-part series on building a GPT from scratch in Elixir. Autograd, computation graphs, and making numbers remember. matthewsinclair.com/blog/0190-wh... #blog #braingasm #ai #gpt #elixir #fromscratch
Blog #0189: The Unreasonable Effectiveness of the Highlander Rule matthewsinclair.com/blog/0189-th... #blog #braingasm #agentic #ai #highlander
Blog #0188: On Knowing What Code to Throw Away Agentic coding has inverted the job — from knowing what to write, to knowing what to throw away matthewsinclair.com/blog/0188-on... #blog #braingasm #agentic #ai
M@ reposted
QFM108: Irresponsible Ai Reading List - March 2026 quantumfaxmachine.com/blog/irrespo... #qfm #blog #quantumfaxmachine #readinglist #irresponsibe #ai #machine #intelligence #genai #generative #ai
M@ reposted
QFM107: Engineering Leadership Reading List - March 2026 quantumfaxmachine.com/blog/enginee... #qfm #blog #quantumfaxmachine #readinglist #engineering #leadership #management #tech
M@ reposted
QFM106: Elixir Reading List - March 2026 quantumfaxmachine.com/blog/elixir/... #qfm #blog #quantumfaxmachine #readinglist #elixir #software #beam
M@ reposted
QFM105: Machine Intelligence Reading List - March 2026 quantumfaxmachine.com/blog/machine... #qfm #blog #quantumfaxmachine #readinglist #machine #intelligence #ai