GPT 6 Sol and Luna
Another insanely good value-for-money offering from OpenAI
Notes tagged ReasoningModels
-
-
Claude Opus 5.5
Better, faster, and cheaper. Doesn't feel like we're slowing down.
-
Qwen3.8-Max
A new frontier model from the Qwen team
-
-
Heavy Thinking: A Test-Time Scaling Pattern for Hard Problems
Now we have GPT Pro at home
-
LLM Reasoning
How LLMs use intermediate reasoning tokens, from chain-of-thought prompting to trained reasoning models, and how this relates to other forms of reasoning.
-
Optimising Computation At The Token-Level
Optimising computation at the token-level
-
Learning to Reason without External Rewards
aka Self-Confidence is All You Need
-
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
learn to reason without any human-annotated data.
-
Large Language Models are Zero-Shot Reasoners (May 2022)
improve zero-shot prompt performance of LLMs by adding “Let’s think step by step” before each answer