7 notes on AI, ML and models people actually use
TypeSafe AI's Jev is the first public System One model: no chat, no tokens, just fast structured decisions software can act on. Why that split matters for agents.
A staged path from Python and classic ML to transformers, evaluation and deployment, with the project at each stage that actually proves you learned it.
Chunking, hybrid retrieval, reranking and honest evals: the parts of a retrieval pipeline that decide whether it works outside a notebook demo.
Quantisation, context budgets and small-model tradeoffs, and the point where running a model on your laptop beats paying per token.
Golden sets, trajectory checks and cheap LLM-as-judge runs wired into CI, so an agent breaking a tool call shows up in a diff and not in a support ticket.
Recall, latency and memory in plain language: what the graph parameters actually trade away, and how to pick them for a real corpus.
When a 1B model with good data beats a frontier model with a clever prompt, plus the dataset, loss curve and eval that convinced me.
← Back home
