topic
LLMs
5 pieces tagged LLMs — notes and essays by Harshal Gajjar on this topic, newest first.
A model trained on everything ever written knows everything ever written. That is a different thing from imagining what hasn't been.
Open-weight models on owned hardware cost nothing per call. Claude Opus is billed per token and is better at almost everything. So the point where the cloud…
The chat-vs-UI divide isn't about interfaces. It's about who holds the model of the task.
The distinction isn't human vs. machine. It's what gets inspected.
We built them on the info-transfer view of language. The places they feel hollow tell us what that view missed.