Looking up through the centre of an internal spiral staircase in a cream/white interior towards a blue skylight. Blog #0194: The Time Cost of How Is Zero Agentic coding pushes the implementation cost of software towards zero. The value shifts from how to build something towards why and what. But this is just the latest rung on a very old ladder.

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

More stylised blue lines with white glowing orb spheres over a flowing digital background. Blog #0193: Learning and Dreaming Part 4 of 4. Cross-entropy loss, Adam optimizer, the training loop, and autoregressive sampling. The GPT learns and generates.

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

Blue, purple, and green stylised swirls on a dark background. Blog #0192: How Tokens Talk to Each Other Self-attention, multi-head projections, and KV caching — the core of the transformer

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

Matrix-inspired green hieroglyphs on a dark background. 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.

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

Stylised graph of blue connected nodes and lines on a dark background. 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.

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

An image of The Highlander from the 80s sci-fi fantasy film of the same name. Blog #0189: The Unreasonable Effectiveness of the Highlander Rule A simple rule with a pithy name turns out to be surprisingly effective at keeping agentic coding on the rails

Blog #0189: The Unreasonable Effectiveness of the Highlander Rule
matthewsinclair.com/blog/0189-th...

#blog #braingasm #agentic #ai #highlander

A greyscale picture of the head of The David by Michaelangelo. 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

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

Lost in #music ... More seriously, treated myself to this gear, and DJing is having a fab effect on my nervous system
#Pioneer #FLX2 #braingasm

An AI-generated example screenshot of an Emacs-like editor editing a Markdown file. Today's #braingasm post explains how to make Emacs appear in macOS Finder’s “Open With” menu for .md files by manually associating file types using duti.

Today's #braingasm post explains how to make Emacs appear in macOS Finder’s “Open With” menu for .md files by manually associating file types using duti.

#0180: Making Emacs Appear in macOS Finder's Open With Menu for Markdown Files
matthewsinclair.com/blog/0180-ma...

Two folders on a computer disk, one for 2023 and one for 2024.

Every week, I try to read or learn something interesting—sometimes useful, sometimes whimsical, occasionally random. Here’s my ‘This Week I Learned’ list for 2024. Enjoy!

matthewsinclair.com/blog/0173-52...

#blog #braingasm #thisweekilearned #2024

matthewsinclair.com · Intelligence. Innovation. Leadership. Influence.

Writing software is 20% syntax and 80% wisdom. Which bit do you think LLMs are good at?

#blog #braingasm #software #engineer #programming #code #llm #genai

#0171: Will Large Language Models Ever Completely Take Over Coding from Human Software Engineers?
matthewsinclair.com/blog/0171-wi...

#0168: FinovateEurope 2024 Summary Insights Demos I went to Finovate and listened to 35 fintech demos so you didn’t have to

#0168: FinovateEurope 2024 Summary Insights Demos

#blog #braingasm #finovate #finovateeurope

medium.com/@matthewsinc...

#0167: A few thoughts on the Apple Vision Pro after a 20 min test drive I wore an AVP on my head for 20 mins and lived to tell the tale

#0167: A few thoughts on the Apple Vision Pro after a 20 min test drive: I wore an AVP on my head for 20 mins and lived to tell the tale

#blog #braingasm

medium.com/@matthewsinc...

#0166: Six Simple Questions to Ask to Ensure You Are Building a Great Product An intentionally simple framework to help early discussions about what to build

#0166: Six Simple Questions to Ask to Ensure You Are Building a Great Product: An intentionally simple framework to help early discussions about what to build

#blog #braingasm

medium.com/@matthewsinc...

#0165: Broad work vs deep work Finding a balance between remote and in-person work

#0165: Broad work vs deep work: Finding a balance between remote and in-person work #blog #braingasm

matthewsinclair.com/ed85419d309c...

#0164: Three Reading Lists Summarising the best links in Machine Intelligence, Elixir, and Engineering Leadership

#0164: Three Reading Lists: Summarising the best links in Machine Intelligence, Elixir, and Engineering Leadership #blog #braingasm #quantumfaxmachine

matthewsinclair.com/0164-three-r...