Lost in the middle: read a long context in parts and summarize each — Thread of Thought beats one gulp

When you paste a long, messy context into a model and ask one question, it skims. Not out of laziness — it's a measured effect. Long-context models show a U-shaped accuracy curve: they use information best when it sits at the very start or very end of the input, and noticeably worse when the same fact sits in the middle. Attention is dominated by primacy and recency. So a decision buried halfway through a sprawling chat thread is exactly where the model is weakest, and a louder distractor at an…