When systems start rewriting their own code
Note: Inspired by thinking about extensions to mostlylucid.mockllmapi and material for the (never to be released but I like to think about it 😜) sci-fi...
Thursday, 13 November 2025 23:00
//
13 minute read
The uncomfortable question we've been avoiding
Note: Inspired by thinking about extensions to mostlylucid.mockllmapi and material for the (never to be released but I like to think about it 😜) sci-fi...
Thursday, 13 November 2025 23:00
//
10 minute read
Building a Multi-LLM Synthetic Decision Engine with LLMockApi
Hey, ever wonder what you could do if you had your own GPU farm?
Note: Inspired by thinking about extensions to mostlylucid.mockllmapi...
Thursday, 13 November 2025 23:00
//
41 minute read
NOTE: This is an old article I forgot to release. Here it is, enjoy! I updated it but may be some issues I missed.
CQRS and Event Sourcing - two patterns that are often mentioned together but...
Thursday, 13 November 2025 12:00
//
19 minute read
WARNING: THESE ARE DRAFT POSTS WHICH 'ESCAPED'.
It's likely much of what's below won't work; I generate these as how-to for ME and then do all the steps and get the sample app working...You've been...
Wednesday, 12 November 2025 22:45
//
14 minute read
WARNING: THESE ARE DRAFT POSTS WHICH 'ESCAPED'.
It's likely much of what's below won't work; I generate these as how-to for ME and then do all the steps and get the sample app working...You've been...
Wednesday, 12 November 2025 22:45
//
13 minute read
WARNING: THESE ARE DRAFT POSTS WHICH 'ESCAPED'.
It's likely much of what's below won't work; I generate these as how-to for ME and then do all the steps and get the sample app working...You've been...
Wednesday, 12 November 2025 22:45
//
16 minute read
WARNING: THESE ARE DRAFT POSTS WHICH 'ESCAPED'.
It's likely much of what's below won't work; I generate these as how-to for ME and then do all the steps and get the sample app working...You've been...
Wednesday, 12 November 2025 22:45
//
16 minute read
Welcome to Part 4! We've set up our GPU (Part 2), understand embeddings and vector databases (Part 3), and have the overall architecture (Part 1). Now it's time to build the ingestion pipeline - the...
Wednesday, 12 November 2025 22:45
//
25 minute read
Welcome to Part 3! We've got our GPU stack working (Part 2), and we understand the architecture (Part 1). Now it's time to dive into the magic that makes semantic search possible: embeddings and...
Wednesday, 12 November 2025 22:45
//
21 minute read
Welcome to Part 2! In Part 1, we laid out the vision for building a writing assistant that uses your blog as a knowledge base - like how lawyers use LLMs trained on case law to draft documents. Now...
Wednesday, 12 November 2025 22:45
//
21 minute read
Buckle in because this is going to be a long series! If you've been following along with this blog, you'll know I'm a bit obsessed with finding interesting ways to use LLMs and AI in practical...
Wednesday, 12 November 2025 22:45
//
17 minute read
In my 8-part "Lawyer GPT" series, I showed you how to build a complete local RAG-based writing assistant using GPU acceleration, local LLMs, and vector databases. It's powerful, private, and runs...
Wednesday, 12 November 2025 22:45
//
24 minute read
While in this current 'manic' article writing stage I thought I'd share a sensitive project I built for a charity during COVID. This is a very sensitive topic so I have gotten all applicable...
Tuesday, 11 November 2025 18:00
//
22 minute read
Over the years I've read / written hundreds of feature specifications. Some were brilliant; most were bloody awful. The difference between a good spec and a bad one isn't about length or formality;...
Tuesday, 11 November 2025 11:30
//
63 minute read
Over the past year, I've stumbled, experimented, broken things, and gradually modernised the frontend build pipeline for this blog. This wasn't some masterplan executed flawlessly—it was trial and...
Tuesday, 11 November 2025 02:15
//
28 minute read
I’ve been putting together a proper filter bar for the blog list: language, date range, sort, and pagination that stays snappy with HTMX. It’s close now—but as always, the last 20% is the spicy bit:...
Monday, 10 November 2025 14:10
//
5 minute read
Over the last few days I've been hammering away at the new blog filter bar: language selection, ordering, and a date range picker that tries very hard to be smart (sometimes too smart). This post...
Monday, 10 November 2025 09:00
//
11 minute read
NOTE: This is part of my experiments with AI / a way to spend $1000 Calude Code Web credits. I've fed this a BUNCH of papers, my understanding, questions I had to generate this article. It's fun and...
Sunday, 09 November 2025 16:00
//
16 minute read
If you've been following this blog, you know I'm a bit obsessed with machine translation. I've written about using EasyNMT, building background translation services, and even improving EasyNMT. But I...
Sunday, 09 November 2025 14:30
//
23 minute read
