What a language model is, without the jargon
- 01Predicting the next word, nothing more6 min
A language model does only one thing: predict the most probable fragment of text to follow what it has already read, and a made-up answer comes out of the same calculation as an accurate one, with no internal signal telling them apart.
- 02The token and the window, what the model actually sees7 min
The model sees tokens stacked inside a window with a fixed ceiling, not whole words taken one by one, and a conversation approaching that ceiling changes content before it even reaches its maximum cost, since Claude then summarises the oldest exchanges.
- 03The myth of the magic setting6 min
Two different answers to the same question do not signal a fault: they come from an internal setting, temperature, which adjusts the risk taken in choosing the next word, and this setting does not fix a poorly phrased request, the request itself can.
- 04One family of models, a choice between speed and depth7 min
The models within the same family share the same base training and really only differ in the trade-off between how fast the answer comes and how deep the reasoning applied before answering goes.
- 05Meaning without a dictionary, and why order matters6 min
Claude opens no dictionary, it associates each word with words of similar meaning and weighs each one against all the others at the moment of answering, which means the place of an instruction in the message changes its real weight in the answer.
- 06How Claude learned to answer, and up to when7 min
Claude goes through three training stages before any conversation, a broad reading of the world, an adjustment into a useful assistant, then self correction grounded in written principles, and the resulting knowledge stops at a date that varies by model.