It is perhaps a sign of the times we live in that many local councils now run commercial advertising on their websites. I couldn’t quite place why that bothered me until today. I was browsing Wals...

Small Things Claude I was testing different models for NER and needed to add two columns to a table and adjust my pipeline a bit. I decided to use Claude code in the CLI, and in an effort to be he...

I’ve been thinking about outliers a lot this week, after a hypothetical scenario came true. UK FOI law requires that you use an acceptable form of your real name when making a request - John Smith ...

The impact of AI on UK FOI requests For a while now, I’ve noticed a steady increase in FOI requests that appeared to me to have been written almost entirely by AI. This weekend, I thought I’d look...

When releasing information under the Freedom of Information Act, public authorities often attempt to redact documents by obscuring sensitive text using black boxes. When this is done incorrectly, t...

In my last post, I mentioned that I’d finally managed to crack how to extract meaningful data from ~3.2 million emails that I’d scraped from WhatDoTheyKnow. I thought it was worth jotting down. Ov...

FOI data After years of chipping away at it, I finally worked out how to extract the answers from FOI responses in a way that is not susceptible to hallucination, and that, as a welcome byproduct, ...

This is not quite a one armed bandit, but the closest I could get in a Gradio space 😁. https://huggingface.co/spaces/HMC83/request-generator It’s running one of the OLMo fine-tunes at the moment....

I recently trained a ~645M parameter LLM from the ground up. This was by far the largest model that I have attempted to create to date. I wanted to train a “good enough” base model that was fully m...

Искам да запиша за малките неща. Върнах се към този език, който бях изоставила. С езика се връща и ентусиазмът. Няма бързината и топлината на родния език, но има нови думи и нов начин да видя нещат...