The edge of the map: what LLMs can't do
Every LLM limit traces back to one fact: it predicts plausible tokens, not truth.
1The model just answered this multiplication. Tap its answer to check it.your turn
the model answeredillustrative
4839 × 271 = 1,310,569
→ continue← backR replay
All of this runs on real silicon, let's see the hardware underneath.
S.1 Why GPUs beat CPUsBuilds on5.1The model is frozen and stateless5.3Tools & agents: the loop around a frozen model7.7The lethal trifecta
Common questions
What is "The edge of the map: what LLMs can't do" about?
Every LLM limit traces back to one fact: it predicts plausible tokens, not truth.
What problem does it solve?
You now know how the whole machine works. So where does it hit a wall, and why, straight from the mechanism?
What will I be able to do after this lesson?
You can name the fundamental limits of LLMs and tie each one to the mechanism that causes it.
What comes next?
All of this runs on real silicon, let's see the hardware underneath.