Skip to content
SamplePreview build: teacher profiles, ratings, reviews and lesson counts are sample data.
Log inFind a tutor

Teacher since March 2026

Bastian Weber

I explain how language models really work, from tokens to attention, without hand waving

9

tutors built

4.5Sample

average from 24 reviews

525Sample

lessons taught by their tutors

About Bastian

I like taking the mystery out of language models. I teach what happens between typing a question and reading an answer: tokens, context windows, embeddings, attention, training and fine tuning. I start every topic with a picture or a small worked example and only add maths when it earns its place. My work background is in software and teaching workshops for people who use these systems but never had them explained properly. I care about precision: I will tell you when an analogy breaks down and where researchers still disagree. If you leave a lesson able to explain the idea to a friend, I have done my job.

Knows about

  • How language models work
  • tokens
  • context windows
  • embeddings
  • attention
  • transformers
  • training and inference
  • fine tuning
  • hallucination

Tutors by Bastian

9 tutors

Why language models make things up

Why language models make things up

Understand the causes of hallucination and build habits that catch it before it costs youAll levelsAI safety and ethics4.4(5)122 lessonsSampleBastian Weber$5Next word prediction from the ground up

Next word prediction from the ground up

See how predicting one word at a time produces whole answers, and what temperature changesBeginnerHow language models work4.5(4)86 lessonsSampleBastian Weber$3Context windows and why chats forget

Context windows and why chats forget

Understand a model's working memory and how to keep long conversations on trackBeginnerHow language models work4.7(3)66 lessonsSampleBastian Weber$4Tokens: how models read text

Tokens: how models read text

See how text becomes tokens and why that explains odd model behaviour, limits and costsBeginnerHow language models work4.7(3)54 lessonsSampleBastian Weber$4Embeddings: meaning as numbers

Embeddings: meaning as numbers

See how words and documents become vectors, and why similar meanings end up close togetherIntermediateHow language models work4.7(3)52 lessonsSampleBastian Weber$6From pretrained model to helpful assistant

From pretrained model to helpful assistant

Learn how instruction tuning, preference training and system prompts turn a predictor into an assistantAdvancedHow language models work4.5(2)51 lessonsSampleBastian Weber$9The attention formula, step by step

The attention formula, step by step

Work through queries, keys, values and softmax by hand until the transformer equation makes senseAdvancedHow language models work4.5(2)48 lessonsSampleBastian Weber$9Training versus inference, clearly

Training versus inference, clearly

Learn what happens when a model is trained, what happens when you use it, and why it mattersIntermediateHow language models work4.5(2)46 lessonsSampleBastian Weber$5Attention without the maths

Attention without the maths

Understand how transformers let each word look at the others, explained with pictures and storiesIntermediateHow language models workNewBastian Weber$5

Recent reviews

What students said about Bastian's tutors.

  • Helena R.Sample

    The niche topic experiment was humbling: four of five sources were fake. The 'specific, rare, consequential' checklist is now pinned above my desk.

    On Why language models make things up

  • Tobias K.Sample

    Framing each method as a fix for the previous one's problem made post training finally coherent. The side effects lesson was excellent.

    On From pretrained model to helpful assistant

  • Pedro A.Sample

    I work in a law office. The real sanctions cases and the quoting technique were exactly what our team needed.

    On Why language models make things up

  • Greta N.Sample

    Very good, if slightly long on causes before getting to fixes. The grounding lesson changed how I summarise reports.

    On Why language models make things up

  • Amina K.Sample

    Clear and useful. Would have liked more on how specific apps handle uploads, though I understand why it stays general.

    On Context windows and why chats forget

  • Soren H.Sample

    Honest about the king and queen example being cherry picked. The negation limit explained a search bug we had.

    On Embeddings: meaning as numbers