2026-08-29 18:19 UTC
@troed@swecyb.com @briankrebs@infosec.exchange really? GenAI is not meant to be a smart database? Have you told Google this as they replace Google Search with GenAI responses?
Also, in both my mentioned examples, I wasn't using it as a database. I was using it to help design and build a system. It was a disaster.
I guess I'm just holding my phone wrong like millions of other GenAI users. #iPhone You're right, it's me not the technology that is prone to errors and bullshit (and fragile).
#GenAI #LLM #AISlop
Replies (1)
-
@troed@swecyb.com 2026-08-29 18:35
@seanm@infosec.exchange Let me quote myself: "consider LLMs to be an absolutely fantastic tool for all use cases that have a clear OK/NOK gate. That involves cybersec, sysadm, software dev, maths proofs etc. It does not include transcribing doctor's notes into patient journals, as a counter example." LLMs are horribly bad at being databases. No one who knows anything about computer science thinks otherwise, no, not the people creating them either. Try it yourself: A good capable local LLM is about 20 GBs in size. With what you know about compression (Shannon's theorem) - can that file include all the knowledge on the planet? @briankrebs@infosec.exchange