How ML Model Data Poisoning Works in 5 Minutes

Re:How ML Model Data Poisoning Works in 5 Minutes by thesz on Sunday March 24, 2024 @07:13PM (#39811385)

I recently made a comment that neural models cannot provide chain of reason, while symbolic methods can: https://news.ycombinator.com/item?id=39759033

The vulnerability in the post is directly linked to that inability, in my opinion.

[ Parent | on HN ]

Re:How ML Model Data Poisoning Works in 5 Minutes by mr_toad on Sunday March 24, 2024 @09:07PM (#39812010)

Current ANN are probably just not big enough to properly reason. We’re still working with the equivalent of insect sized brains. We shouldn’t assume that future ANN will not be capable of deductive reasoning.

Also LLMs might not be the best approach for deductive reasoning, but LLMs are not the only architecture.

[ Parent | on HN ]