Blog
Writing
Life, tech, and everything in-between.
Graph-of-Thought: Non-Linear Reasoning with Merge and Refine
7 minAI
Trees branch and backtrack but never merge or loop. Graph-of-Thought extends the search to a directed graph, adding aggregation of parallel branches and refinement of earlier thoughts. The payoff is on problems that need synthesis rather than pure search.
Evaluator-Optimizer: Iterative Refinement with a Separate Critic LLM
7 minAI
Some tasks improve on a second pass, but only when the critic is a separate LLM with its own mandate. Asking a generator to grade its own work produces confident praise for mediocre output.