🤖

Series · Part 7 of 21

Foundation
AI Demystified
Abhishek Saha
Abhishek Saha · 🤖 AI / ML

What AI Cannot Do

8 structural limitations of every language model — not bugs, not temporary — built into how they work. Illustrated.

#ai #limitations #reasoning #reliability #philosophy
What AI Cannot Do

AI is impressive and limited in equal measure. The limits aren’t random — they’re structural. Knowing them is what separates people who get reliable results from people who get burned.

LIMITATION EXPLORER
What AI Cannot Do
1 / 8 — click any card
◎
WEIGHTS FREEZE AT TRAINING

No Persistent Memory

Once training ends, the model's weights are locked. Every conversation starts fresh. Your corrections vanish the moment the session ends — they never touch the underlying model.

🔒
WEIGHTS FROZEN
at training
your correction
↩ bounces off
Session 1 — fresh start
Session 2 — fresh start
Session 3 — fresh start
every session resets — nothing persists
IMPLICATIONDesign workflows that re-supply context every session. Don't expect the model to remember yesterday's corrections.

These aren’t temporary bugs. They’re consequences of how Transformers work — pattern completion over frozen weights. Better models reduce the severity, not the shape, of these limits.

Next up: Part 8 covers reasoning models — and how making AI “think longer” actually helps with some of these.

AI Demystified · 16 of 21 published

  1. 0 Grounding 5 Mental Models You Need Before Diving Into AI
  2. 1 Foundation What Happens When You Ask AI Something?
  3. 2 Foundation Transformers — The Architecture That Changed Everything
  4. 3 Foundation How AI Learns, Thinks, and Decides
  5. 4 Foundation How AI Reads Your Words
  6. 5 Foundation Why AI Forgets
  7. 6 Foundation Why AI Lies (And Doesn't Know It)
  8. 7 Foundation What AI Cannot Do
  9. 8 Foundation How AI Reasons (And Why It Sometimes Breaks)
  10. 9 Practice Prompt Engineering — How to Talk to AI
  11. 10 Practice Embeddings & Vector Databases — The Memory Layer of AI
  12. 11 Practice RAG Explained — How AI Knows What You Didn't Train It On
  13. 12 Practice Fine-tuning vs. Prompting — When to Use Which
  14. 13 Practice Do You Really Need GPT-4?
  15. 14 Practice Latency, Tokens, and Cost — The Physics of AI Products
  16. 15 Practice How Do You Know AI Is Actually Working?
  17. 16 Hands-On Coding Setup — Your AI Development Environment soon
  18. 17 Hands-On MCP Tool Calling — How AI Uses Tools soon
  19. 18 Hands-On AI Agents — Beyond Chatbots soon
  20. 19 Hands-On Build Your First Real AI App soon
  21. 20 Hands-On Token Optimization — Spend Less, Get More soon
← Part 6 Why AI Lies (And Doesn't Know It) Part 8 → How AI Reasons (And Why It Sometimes Breaks)
newsletter

Get new posts in your inbox

No spam. No digest. Just a note when I publish something new.

Discussion