News for hackers. Stuff that matters.
Re:AI Agents Ask Better Questions Than KPMG Accountants in L... by kridsdale1 on Wednesday November 18, 2026 @03:51PM (#50551951)
It does tire, that’s context rot. It’s just that AI can rest and reawaken fresh as fast as you can write “compacting…”
Re:AI Agents Ask Better Questions Than KPMG Accountants in L... by mikepurvis on Wednesday November 18, 2026 @03:58PM (#50552045)
Better yet, your initial agent can spawn dozens or hundreds of fresh minions that each look in excruciating detail at one small area, then other agents that analyze their reports and look for potential issues that span their domains.

Much as with real people, the context window is addressed through collaboration, and it turns out agents are extremely good at that too.

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.
Re:AI Agents Ask Better Questions Than KPMG Accountants in L... by yen223 on Wednesday November 18, 2026 @08:47PM (#50555066)
for comparison, this whole comment thread is roughly 10k tokens.

how well would a human fare, trying to recall the details from ten of these?