LLMs can’t reason — they just crib reasoning-like steps from their training data

David Gerard@awful.systems · 23 days ago

LLMs can’t reason — they just crib reasoning-like steps from their training data

froztbyte@awful.systems · 21 days ago

I know someone who was hired (around turn of the century) because they knew how to xml with a certain kind of then-important big systems api

the stories I’ve heard from there are hilarious

but is also incredibly ease to create proprietary semantics with

christ the shit I’ve seen with network vendors…. shibboleth NETCONF/YANG. advance warning; abyss grade 6+

bitofhope@awful.systems · 21 days ago

And yet there are some tasks I wish I could do in NETCONF instead of the thing we’re actually using, but apparently the documentation for this interface is difficult and expensive for the company to get my hands on, for reasons.

froztbyte@awful.systems · 21 days ago

ikwym, that’s part of the set of crimes I was pointing to

bitofhope@awful.systems · 21 days ago

LLMs can’t reason — they just crib reasoning-like steps from their training data

LLMs can’t reason — they just crib reasoning-like steps from their training data

LLMs can’t reason — they just crib reasoning-like steps from their training data – Pivot to AI