Re:AI Agents Ask Better Questions Than KPMG Accountants in L...
by formerly_proven on Wednesday November 18, 2026 @04:19PM
(#50552256)
Most models start to noticeably degrade around the 100k token neighborhood, which is still hundreds of pages of text that can be attended to more or less densely.
Much as with real people, the context window is addressed through collaboration, and it turns out agents are extremely good at that too.