is AI actually thinking, or is it just guessing words?

It guesses the next word, over and over, very fast, using everything before it including what it just wrote. Nothing in that loop stops to look anything up. That one fact explains why it drafts a vendor email beautifully and invents a tag number just as beautifully.

why does the AI forget what I told it in another chat?

Everything it can see is what is in the chat in front of it: what you pasted, what it has written, and your new question. Your inventory system, Metrc and yesterday's chat are not in there unless you paste them in or connect them. Nothing carries over on its own.

What an AI Chatbot Actually Is · No Bullshit AI Cannabis Course

Questions this answersQuestions this answersfaq

is AI actually thinking, or is it just guessing words?is AI actually thinking, or is it just guessing words?what is an LLM actually doing when it answers?: It guesses the next word, over and over, very fast, using everything before it including what it just wrote. Nothing in that loop stops to look anything up. That one fact explains why it drafts a vendor email beautifully and invents a tag number just as beautifully.It guesses the next word, over and over, very fast, using everything before it including what it just wrote. Nothing in that loop stops to look anything up. That one fact explains why it drafts a vendor email beautifully and invents a tag number just as beautifully.Autoregressive next-token prediction: it produces a distribution over the next token, samples one, appends it and repeats until a stop token. There is no retrieval step and no separate truth check, so fluency and correctness are decoupled by construction.
why does the AI forget what I told it in another chat?why does the AI forget what I told it in another chat?what is a context window, and what falls outside it?: Everything it can see is what is in the chat in front of it: what you pasted, what it has written, and your new question. Your inventory system, Metrc and yesterday's chat are not in there unless you paste them in or connect them. Nothing carries over on its own.Everything it can see is what is in the chat in front of it: what you pasted, what it has written, and your new question. Your inventory system, Metrc and yesterday's chat are not in there unless you paste them in or connect them. Nothing carries over on its own.The context window is the model's only state. Nothing outside it exists: not the ERP, not Metrc, not a prior session. Chat memory features are notes re-inserted at the start of a new context, and they still have to fit the budget.

Read the rest for freeSign in to read the restauth required past this point

A name and an email, once. The whole course is free, nothing is sold to you, and your place is kept so you can pick it up on your phone later.A name and an email, once. The course is free; the account exists so your progress and your level on the dial follow you between devices, and so you can be issued a certificate at the end.name + email. free. account carries completion state, data-level and certificate issuance.

We store your name, your email, which lessons you open and which you finish, and the reading level you use. Distru can see that. Nothing is charged and nothing is sold on.Stored: name, email, which lessons you open and complete, and your level on the dial. Distru staff can see it. No payment, no third-party advertising trackers.stored: name, email, per-lesson view + completion, data-level. visible to Distru. no payment, no ad-tech, no third-party pixels.

Adapted from Microsoft's Generative AI for Beginners (Lesson 1: Introduction to generative AI, Lesson 4: Prompt engineering fundamentals), MIT License. Rewritten for cannabis operations; not endorsed by Microsoft.