Why LLMs Think Longer?
Learn how modern language models use extra inference-time computation to improve reasoning, why those methods work best on verifiable tasks, and where visible chain-of-thought can mislead. This course is for technically curious learners with basic LLM familiarity.
4 sections ยท 11 lessons
Course outline
Compute Budget
- Slow Thinking for Models
- Inference Compute as a Resource
Reasoning Paths
- Chain-of-Thought as Scratchpad
- Branching and Revision
Training and Trust
- RL on Verifiable Tasks
- Tools as Reliable Substeps
- Faithfulness Under Pressure
Hidden and Scaled
- Thinking Beyond Words
- Latent Thoughts and EM
- Self-Taught Reasoning Loops
- When Thinking Longer Scales