Embeddings and vector similarity
By the end of today you can explain what an embedding represents, compute similarity between two pieces of text, and say precisely when semantic search beats keyword search and when it loses to it.
YesterdayOn Day 15 you learned hashing scatters similar keys deliberately, which is why a hash map cannot answer 'find me something like this'. Embeddings solve exactly that problem.
TomorrowTomorrow you use them at scale: chunking documents, indexing them, and retrieving the right ones.
Why this matters
Embeddings are how software finds things by meaning rather than by exact words. Understanding what they can and cannot capture is what stops retrieval systems failing mysteriously.
- Embeddings
- Cosine similarity
- Semantic against keyword search
- What embeddings miss
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.
6 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
45 minEmbed six short sentences: three about one topic, three about another, including one pair where the second negates the first. Compute the full similarity matrix and print it. Identify the highest-similarity pair that should not be similar, and write two sentences on what that means for a retrieval system.
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
- 01An embedding places text in a space where nearby means similar in meaning
- 02Cosine similarity compares direction, ignoring length
- 03Embeddings are model-specific, so changing model means re-embedding everything
- 04Negation and exact identifiers are where embeddings fail hardest
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.