The basic "Learning AI" collection

[Chip (OP)]

This should get you up to speed, in this order:

1. The First AI - Samuel’s Checkers ML System
https://forum.drugs-and-users.org/index.php?topic=7338

Historical grounding.
Shows the origins of machine learning and self-improving systems.

2. What the basic components of AI are and how the data flows
https://forum.drugs-and-users.org/index.php?topic=7347

High-level architectural overview before deep diving.

3. How Neural Networks Work
https://forum.drugs-and-users.org/index.php?topic=7343

Core foundation.
Everything modern comes from this.

4. The AI Tokenisation Pipeline
https://forum.drugs-and-users.org/index.php?topic=7350

Now the reader understands WHY text must become vectors and embeddings.

5. Transformers
https://forum.drugs-and-users.org/index.php?topic=7344

The real breakthrough architecture behind modern LLMs.

6. A light intro to LLMs, chatbots, pretraining, and transformers
https://forum.drugs-and-users.org/index.php?topic=7342

Applies the transformer concept to actual LLM systems and chatbot behaviour.

7. RAG - Retrieval Augmented Generation
https://forum.drugs-and-users.org/index.php?topic=7348

Advanced modern extension layer.
Shows how models interface with external knowledge.


Those were the basics and once you roughly understand them then continue on with the following topics:


8. Embeddings and Vector Spaces
https://forum.drugs-and-users.org/index.php?topic=7351

Right now embeddings are probably buried inside tokenisation or neural networks, but embeddings are absolutely central to modern AI.

Topics:

• What embeddings actually are
• High-dimensional vector spaces
• Semantic proximity
• Why "cat" and "dog" cluster together
• Cosine similarity
• Latent space
• Why RAG works
• Why hallucinations happen

This becomes the bridge between:

Code: [Select]

Token IDs → Meaning Space

9. Attention Mechanisms and Self-Attention

Transformers really deserve to be split and Attention is the actual revolutionary mechanism.

Topics:

• Query / Key / Value vectors
• Attention weighting
• Context windows
• Token relationships
• Parallel processing vs recurrence
• Why transformers replaced RNNs/LSTMs

Without attention, transformers look like magic.

10. Training vs Inference

This is one of the most misunderstood things in AI discussions.

Most people think ChatGPT is "learning while talking."

It usually is not.

Topics:

• Pretraining
• Gradient descent
• Backpropagation
• Weights
• Inference-only operation
• Fine tuning
• RLHF
• Why models are static snapshots

This clears up enormous confusion.

11. Context Windows and Memory

Critical for chatbot understanding.

Topics:

• What context windows are
• Token limits
• Sliding attention windows
• Conversation truncation
• Why models "forget"
• Persistent memory systems
• RAG vs memory

This directly explains chatbot behaviour.

12. Hallucinations and Failure Modes

Very important.

Topics:

• Probabilistic generation
• Why confidence ≠ correctness
• Distribution gaps
• Mode collapse
• Confabulation
• Context poisoning
• Prompt injection

Most people fundamentally misunderstand hallucinations.

13. Multi-Modal AI

Modern systems are no longer just text.

Topics:

• Vision transformers
• Image tokenisation
• Audio embeddings
• Cross-modal embeddings
• Unified latent spaces
• Image generation diffusion models

This connects LLMs to image/video/audio systems.

14. Agents and Tool Use

Modern frontier AI architecture.

Topics:

• Tool calling
• External APIs
• Planning loops
• Chain-of-thought orchestration
• Autonomous agents
• Memory stores
• Execution environments

This is where systems are heading now.

15. Scaling Laws

Very important historically.

Topics:

• Why bigger models suddenly worked
• Emergent behaviour
• Parameter scaling
• Data scaling
• Compute scaling
• Why GPT-3 changed everything

This explains why AI progress looked sudden.

16. Diffusion Models

Needed if discussing image generation.

Topics:

• Noise schedules
• Denoising
• Latent diffusion
• Classifier guidance
• Why Stable Diffusion works

Completely different architecture family from transformers.