Fast, slow, and neither

The System 1 / System 2 story everyone tells about AI, how much of it the evidence actually supports, and where TypeSafe’s Jev sits — a model that answers without writing anything, on neither axis.

5 concepts, about 30 minutes of reading at roughly six minutes each. Every concept in this track needs a paid plan.

What is in this track

1. Two systems that were never two systems — The fast/slow vocabulary everyone borrows for AI was coined by psychologists who later abandoned it, and popularised by one who called the two systems fictitious characters.
2. Paying for the pause — Letting a model produce more tokens before it answers really does make it more accurate — and it is the most expensive sentence in this course.
3. The reasoning you can read — A model that shows its working is not necessarily showing you its working. Several experiments separate the two, and the gap is large.
4. Jev, the model that will not talk — TypeSafe’s Jev is a System One model: it does not produce text at all. It reads a state, answers typed questions in one shot, and hands back probabilities.
5. Choosing between the three — Most tasks announce which kind of model they want, as soon as you ask whether you need a sentence or a decision.

Before this: Trust and evals

Every track · Pricing · Claims we checked and could not stand behind