Legal software used to follow rules. This lot reads. Most of the legal tech I have used in 25 years followed rules. Type a citation, get the case. Tick “contract”, get the contract fields. Useful, but it is a clerk. Fast, exact, and completely unable to read a record and tell you what is odd …
Category Archives: Notes
Why LLMs make things up
Because we taught them that guessing pays. Picture a multiple-choice exam with no negative marking. Right answer, one mark. Wrong answer, nothing. Leave it blank, nothing. Any student worth their salt guesses every time. You can never do worse. In September 2025 a group of OpenAI researchers argued that this is how language models are …
How LLMs work, in plain English
It predicts the next word. Then it does it again. Strip away the jargon and a large language model does one thing. Given the text so far, it gives a score to every possible next piece of text, picks one, adds it, and goes again. The pieces are called tokens, which are words or bits …
Lawyers are small language models
We were doing this long before the machines. Think about how a junior learns. Years of reading judgments, heads, pleadings, affidavits. Nobody hands you the rules for how a court writes. You soak it up. After a while you can guess what the next paragraph of a judgment will say before you turn the page. …
How OCR works, and why it never tells you it guessed
A scan is a photograph of words. OCR is the bit that tries to turn it back into words. When you scan a page, the computer does not get words. It gets a picture. Millions of dots, some dark, some light. To you it says “the respondent is not liable”. To the computer it is …
Continue reading “How OCR works, and why it never tells you it guessed”