News for hackers. Stuff that matters.

A comment on Things we learned about LLMs in 2024. Parent comment

Re:Things we learned about LLMs in 2024 by HarHarVeryFunny on Thursday January 02, 2025 @07:39AM (#42573915)
The inner workings/representations of transformers/LLMs aren't a total black box - there's a lot of work being done (and published) on "mechanistic interpretability", especially by Anthropic.

The intelligence we see in LLMs is to be expected - we're looking in the mirror. They are trained to copy humans, so it's just our own thought patterns and reasoning being output. The LLM is just a "selective mirror" deciding what to output for any given input.

[ Parent | on HN ]
Re:Things we learned about LLMs in 2024 by Jerrrry on Thursday January 02, 2025 @11:20AM (#42575769)
Its mirroring the capability (if not currently the executive agency) of being able to convince people to do things. That alone gaps the barrier as social engineering is impossible to patch - harder than full proofing models against being jailbroken/used in an adversarial context.
[ Parent | on HN ]