Reasoning Models
Test-time compute, process reward models, the o-series, DeepSeek-R1 and contamination.
9concepts
46flashcards
74minutes of reading
- 01 Chain of Thought, Self-consistency, and Search at Inference A tour of the inference-time reasoning toolkit - from zero-shot CoT prompts to MCTS-decoded reasoning trees, and when each pays for itself.
- 02 OpenAI o1, o3 and the Reasoning-Model Family What is publicly known and what is speculated about OpenAI's reasoning line, why the chain of thought is hidden, and what o3's ARC-AGI result actually proved.
- 03 Reasoning Evals and the Contamination Problem A guided tour of the reasoning benchmark canon, why each saturated faster than the field expected, and the move to live held-out evals as the contamination crisis bites.
- 04 Test-time Compute Scaling Why "thinking longer" at inference can substitute for "training bigger", how the trade-off is operationalised as a token budget, and where the strategy stops paying.
- 05 Chain-of-Thought Faithfulness Whether a model's stated reasoning is the reasoning that produced its answer, how the hint-injection test measures it, and why unfaithful CoT undermines monitoring more than it undermines accuracy.
- 06 DeepSeek-R1 and the Open Reasoning Recipe How DeepSeek's R1 pipeline produced o1-class reasoning with an open paper, an open model, and a recipe other labs could replicate within weeks.
- 07 Inference-Time Scaling Laws and Thinking Budgets How accuracy trades against tokens spent at inference, why the optimal strategy depends on question difficulty, and what a thinking budget actually buys.
- 08 Process Reward Models and Verifiable Rewards Why scoring every step of a reasoning trace beats scoring only the final answer, and how Ai2 and DeepSeek replaced PRMs entirely with programmatic correctness checks.
- 09 The Limits of Self-Correction Why asking a model to review its own answer often makes it worse, what separates intrinsic from extrinsic correction, and the oracle-label leak that inflated the early results.