Home | GitHub | Twitter

About Me

I'm currently working as an NLP Engineer @ aveni.

I have a PhD from Heriot-Watt University, where my research was on applying natural language processing-based machine learning algorithms to programming languages.

Prior to that, I obtained a First-Class Master's degree (MEng) in Digital Electronics (now known as Electronics and Computer Engineering) from the University of Sheffield.

In my spare time I enjoy: reading, listening to podcasts, playing board games, walking my dog, and watching sports.

Contact

You can contact me on twitter or via e-mail.

Notebooks

Things I've learned, formatted as Python notebooks.

2024-12-15 Making LLMs smarter with structured generation and Outlines
2024-02-17 Introduction to information theory (from a machine learning perspective)
2024-02-10 Decision trees and random forests from scratch
2023-10-03 Bootstrapping confidence intervals
2023-09-27 Parallelism in Python
2023-09-07 Some practical use cases for the walrus operator
2023-08-28 Retrieval augmented generation
2023-08-27 Implementing TF-IDF from scratch
2023-08-06 A/B testing with the chi-squared test
2023-08-03 Fine-tuning a sequence classification model with LoRA and the peft library
2023-07-31 How to use Open AI's "function calling" ability
2023-07-30 What's the best way to strip punctuation from a string?
2023-07-29 Why is the softmax function "off by one"?

Projects

Things that I've worked on.

2026-09 Minesweeper Sudoku: A daily logic puzzle. Hatch half of every row, column and region, guided by numbers counting the filled cells around them, across two grid sizes and three sets of regions. New
2026-08 Tetronimo Place: A daily tiling puzzle. Fill a board using tetronimoes. New
2026-08 122333 Sudoku: A daily logic puzzle. Fill a six by six grid so every row and column holds one 1, two 2s and three 3s, across six sets of rules. New
2026-08 Wordie Place: A daily word puzzle. Put sixteen two letter tiles back on the ends of eight lines so that every line spells a word. New
2026-08 Bee Switch: A daily word puzzle. Slide and stack words from one day's NYT Spelling Bee until the middle column spells a pangram. New
2026-08 Bee Definition: A daily word puzzle. Every answer from one day's NYT Spelling Bee, given only by its definition and its length. New
2026-08 Wordie Down: A daily word puzzle. Reorder five words so the shaded squares spell words running downwards, and find all of them. New
2026-08 Wordie Loop: A daily word puzzle. Build five words into a loop, where the last letter of each is the first letter of the next. New
2026-08 Wordie Grid: A daily word puzzle. Fill a five by five grid so every row spells a word, scoring Scrabble letter values with bonus squares. New
2026-08 Pineapple Grid: A daily solo puzzle. Place cards into a five by five grid, scoring every row and column as a poker hand. New
2026-08 Pineapple Lines: A daily solo puzzle based on Pineapple Open Face Chinese Poker. New
2025-08 The Castles of Burgundy Automata: An implementation of an Automata to play the The Castles of Burgundy board game solo.
2025-07 Forest Shuffle Automata: An implementation of an Automata to play the Forest Shuffle card game solo.
2025-04 repository-template: A repository template for Python projects, using: uv, ruff, pre-commit, and pytest.
2024-04 clip-search: Text-to-image search with OpenCLIP, Docker, Flask, Faiss, etc. and a basic front-end.
2024-04 hackerdaily2hackernews: A Google Chrome extension that redirects from HackerDaily comments to Hacker News comments.
2022-10 lexisearch: Retrieval augmented generation on transcriptions from the Lex Fridman Podcast.
2022-02 GloVedle: A version of Wordle using GloVe embeddings.
2022-02 Wordle Terminal: A Python port of Wordle which is played in the terminal.
2022-01 UUIDv4 Generator: Generate UUIDv4s in the browser, because I didn't like the way the top result on Google generated them.
2021-XX Sentiment Analysis Tutorial: A tutorial on how to implement some common deep learning based sentiment analysis (text classification) models in PyTorch with torchtext, specifically the NBOW, GRU, bi-LSTM, CNN and Transformer models. Somehow got popular and has quite a few stars.
2021-XX Sequence-to-Sequence Learning Tutorial: A tutorial implementing neural (deep learning based) sequence-to-sequence models in PyTorch with torchtext, by implementing six NMT papers. Also has quite a few stars and was used as a basis for the official PyTorch language translation tutorial.
2021-08 easynlp: A library for performing natural language processing - such as zero-shot classification, translation, named entity recognition, summarization, and question answering - inference on given data utilizing the pre-trained models from transformers.
2021-02 Image Classification Tutorial: A tutorial covering how to implement some deep learning computer vision models in PyTorch with torchvision. Covers: a basic multi-layer perceptron, LeNet, AlexNet, VGG and ResNet.
2021-01 A Tour of Optimizers: A tutorial on common optimization algorithms used for neural networks, including: SGD, Adagrad, Adadelta, RMSprop and Adam.
2020-10 numberworld: A reinforcement learning toy environment for task-oriented language grounding.
2020-07 Glyphs of Dialogue: A small project combining ideas from GlyphNet and Dimensions of Dialogue.
2020-03 Recurrent Attention Model: A PyTorch implementation of the Recurrent Attention Model from the Recurrent Models of Visual Attention paper.
2019-03 countworld: Generating synthetic datasets that deal with counting.
2016 snake: Snake in Javascript.
2016 difference: A timed mental maths game in Javascript.
Top