Re:Teach your LLM to answer with facts, not fiction
by delecti on Sunday July 23, 2023 @11:56PM
(#36842969)
Hallucination is a better descriptor for what an LLM is doing though. A bullshitter knows they don't know, an LLM just strings words together in ways that fit what it "saw" from training data. IMO the main problem with calling them hallucinations is the implication that the true things they say are true on purpose. It's hallucinating the true things too.
[ Parent
| on HN ]
Re:Teach your LLM to answer with facts, not fiction
by mdp2021 on Monday July 24, 2023 @03:52AM
(#36844371)
Exactly, but no, there should be no «implication that the true things they» output are not part of that: required modules for foundational thinking (let us say "critical thinking") are missing.
(Issue is, now some are convinced that people in general would do the same and just blurt out the feedforward output of their "internal neural network", as opposed to having built knowledge in a loop of critical evaluation.)
Re:Teach your LLM to answer with facts, not fiction
by ImHereToVote on Monday July 24, 2023 @06:45AM
(#36845718)
In Swedish the term for perception and misapprehension is the same word. Because it is the same thing.