Re:AI Agents Ask Better Questions Than KPMG Accountants in L...
by Zigurd on Wednesday November 18, 2026 @07:19PM
(#50554276)
I don't use LLMs much outside of coding. I find their writing wordy and insipid. But they remember details like a steel trap. Take a topic that's tedious and boring and detailed and ask if you've covered all the bases. That has saved me on a few occasions from being too bored or fatigued to remember everything I should cover on a topic. Auditing sounds like a perfect use case.
[ Parent
| on HN ]
Re:AI Agents Ask Better Questions Than KPMG Accountants in L...
by bagacrap on Wednesday November 18, 2026 @07:26PM
(#50554345)
Auditing seems like it has a lot in common with bug hunting. LLMs are great at finding bugs, that is uncontroversial.
Re:AI Agents Ask Better Questions Than KPMG Accountants in L...
by nradov on Wednesday November 18, 2026 @08:23PM
(#50554872)
In theory, yes. But do the auditors always really want to find every GAAP violation? Sometimes there may be other motivations in play.
Re:AI Agents Ask Better Questions Than KPMG Accountants in L...
by esperent on Wednesday November 18, 2026 @11:37PM
(#50556140)
[delayed]
Re:AI Agents Ask Better Questions Than KPMG Accountants in L...
by InsidiousWombat on Wednesday November 18, 2026 @08:20PM
(#50554846)
I use it a lot for just making sure documentation matches the reality (investing in infrastructure as a code some odd 15 years ago paid off well), or extracting particular element out of it ("descibe and diagram how this one customer apps are connected")
Re:AI Agents Ask Better Questions Than KPMG Accountants in L...
by coolandsmartrr on Thursday November 19, 2026 @12:46AM
(#50556480)
I have a similar experience receiving wordy and insipid output with chatGPT. I'm curious if the quality of writing depends on AI model. Which AI model did you use?