What a language model actually is, for engineers
By the end of today you can describe what happens between sending text and receiving a response, explain why the same input can give different outputs, and say precisely why a model states false things with confidence.
YesterdayFor 66 days you built deterministic systems where the same input always gave the same output. Today that assumption breaks.
TomorrowTomorrow, the units these systems are measured and billed in.
Why this matters
Almost every AI engineering mistake comes from treating a probabilistic component as a deterministic one. Getting this straight on day one of the phase prevents most of them.
- How a model generates
- Probabilistic output
- Hallucination
- The model as a component
Learn it
70 minCopy this into Claude or ChatGPT. It quizzes you before it explains anything, which is deliberate. The resources under it are how you check what it told you.
Today's Master Prompt
Free · sign inA prompt written for this day alone: your level, the exact scope, what to leave out, and an instruction to quiz you before it explains anything. Paste it into Claude or ChatGPT and it teaches you today's material.
Check it against something that is not a model
An assistant can be fluent and wrong, and on a topic you met today you will not catch it. These cover the same ground and were made by people who do this for a living, so they are what you hold the explanation up against. They are other people's work and we only link to them, so judge them for yourself.
5 hand-picked resources
Free · sign inVideos, official docs and articles covering the same ground, each opened and annotated by hand. They are what you check the assistant against on a day you cannot yet catch it being wrong.
Build it
40 minAsk a model the same non-trivial question five times in separate conversations and record how the answers differ. Then ask it something it cannot know: a fact after its training cutoff, or a detail about your own codebase. Record exactly how confident the wrong answer sounded, word for word.
Recall it
25 minAnswer out loud, reveal, then mark honestly whether you had it. That score is the only thing on this page you do not get to choose.
5 recall questions
Free · sign inQuestions you answer from memory, then grade yourself against the real answer. The score is carried into the mastery rating below it, so an honest miss cannot quietly become a tick.
Rate it
Completion and mastery are tracked separately. Be honest, because an inflated rating only means the concept resurfaces sooner.
Mastery tracking
Free · sign inRate yourself against five named criteria per concept. Completion and mastery are tracked separately, and anything you rate shakily comes back automatically on a spaced schedule.
Recap
- 01The model predicts a plausible next token; nothing checks it against reality
- 02Confidence is not computed, so wrong answers sound exactly like right ones
- 03It knows nothing about your systems beyond what you send
- 04It is one component in a system you already know how to build
Your progress
Free · sign inMark days complete, pick up where you left off across devices, and watch completion and mastery diverge. Free, and the account exists only so ninety days of work cannot vanish with a cleared browser.