Danny Wood @echostatements.bsky.social · 09/06/2026It definitely seems more robust with the "the word" phrasing, and sometimes even gives you a Python snippet that can verify the result. But even then it doesn't seem to catch everything. 120 2
Danny Wood @echostatements.bsky.social · 09/06/2026Saying that theres no "i" in team used to mean you were a team player. Now it shows you're yet to embrace the full potential of AI. 110 1
Danny Wood @echostatements.bsky.social · 03/02/2026Can we get LLMs to generate text that is perfectly typeset down to the very last character? In a new blog post, I show how using a constrained beam search, LLMs can efficiently generate perfect blocks of monospace text echostatements.net/posts/2026/0... 110 1
Danny Wood @echostatements.bsky.social · 01/02/2026I've added the ability to create Delaunay triangulations to my Voronoi diagram generation Python library. The image generation takes a few seconds but I'm pleased with how easy it is to make pretty and varied outputs with it 100 1
Danny Wood @echostatements.bsky.social · 23/01/2026And an honourable mention: Lego: Lego Lego supposedly are the world's largest manufacturer of tyres (at least according to the Guinness*). Sure, tyres aren't their main focus, but that doesn't seem so unusual for a tyre company! * While we're at it: yes, Guinness the brewery/word record authority 000 0
Danny Wood @echostatements.bsky.social · 23/01/2026Goodyear: Blimps Unbelievably left-field. In the 20th century, they at least built the blimps themselves, but now their sideline seems to just be being the world's most famous owner of a fleet of airships 100 1
Danny Wood @echostatements.bsky.social · 23/01/2026Michelin: Restaurant reviews This clearly got out of hand for them. It started as a more general guide for motorists, (even that is a slightly eccentric thing for a tyre company) but getting your tyres from the world's foremost authority on restaurant quality is odd 100 1
Danny Wood @echostatements.bsky.social · 23/01/2026Dunlop: Sports equipment If you're working with rubber anyway, I can see how you get into making tennis balls and how that might spiral into sporting goods more generally Fair enough 100 1
Danny Wood @echostatements.bsky.social · 28/09/2025Answering my own question, the example from the "Infinite-dimensional vector function" Wikipedia page makes it feel clear that a curve with these properties will exist Even so, without more thought, this feels more like it side-steps the issue in my intuition than directly tackles it 010 1
Danny Wood @echostatements.bsky.social · 07/08/2025Looking at the code in Hugging Face's library for the new GPT models, I was a bit disappointed by how similar they are to Llama & Mistral models, but there is one cool trick I hadn't seen before: attention sinks. These are a mechanism by which attention heads can say "I don't have anything to add" 120 2
Danny Wood @echostatements.bsky.social · 22/07/2025A little etymological fact that I like is that "lemma" and "dilemma" are from the same ancient Greek origin If you translate "lemma" as meaning a proposition, a dilemma is literally having two propositions to consider 120 2
Danny Wood @echostatements.bsky.social · 18/07/2025And even better, these tricks are not mutually exclusive, by doing both simultaneously, you get a 2.5x speed up (dependent on batch size) 8/9 🧵 100 1
Danny Wood @echostatements.bsky.social · 18/07/2025Again, this gets some pretty significant speed-up 7/9 🧵 100 1
Danny Wood @echostatements.bsky.social · 18/07/2025Optimisation 2: When training Siamese networks, people tend to generate matching/non-matching pairs in equal ratio. However, you can train more efficiently if you generate only matching pairs, then creating the non-matching ones with some shifting of subnetwork outputs. 6/9 🧵 100 1
Danny Wood @echostatements.bsky.social · 18/07/2025Optimisation 1: In practice, when implementing these networks there is only one subnetwork, called twice, once for each input But by stacking the inputs, we actually only need to make one call to the network: Depending on batch size, the effect can be significant 5/9 🧵 110 1
Danny Wood @echostatements.bsky.social · 18/07/2025Firstly, what is a Siamese neural network? A Siamese neural network consists of two identical subnetworks and a comparison layer The two subnetworks generate representations for two different inputs, then the comparison layer measures the similarity between these representations 3/9 🧵 100 1
Danny Wood @echostatements.bsky.social · 18/07/2025Siamese neural networks are a neat way of doing one-shot/few-shot classification but there's something about the way they're usually implemented that felt a bit inefficient to me Here are a couple of relatively simple tricks you can do to speed up training Siamese networks by 2.5x! 1/9 🧵 130 3
Danny Wood @echostatements.bsky.social · 02/05/2025If you've not read it, I highly recommend "Admissible probability measurement procedures" by Shuford et al (1966) too It's really well written and if you replaced "students" with "models" in the text, would read like a fairly modern machine learning paper link.springer.com/article/10.1... 010 1