News for hackers. Stuff that matters.

A comment on Is Robert Frost Even a Good Poet?. Parent comment

Re:Is Robert Frost Even a Good Poet? by schiffern on Wednesday March 26, 2025 @01:30PM (#43484582)
There are many legitimate criticisms of LLMs today. "When you prompt XYZ it has no correlation with whether the LLM does XYZ" isn't one of them. LLMs are way past that stage.

Essentially what you're asking is, "why do you think prompt engineering would work?" That ship has already sailed.

[ Parent | on HN ]
Re:Is Robert Frost Even a Good Poet? by LPisGood on Wednesday March 26, 2025 @03:24PM (#43485991)
No, that’s not what I’m saying. I’m not talking about “LLM [doing] XYZ”. I’m specifically talking about asking an LLM to ignore its training data.

It definitionally cannot do that. It can obey other values of XYZ, but certainly not this one.

[ Parent | on HN ]
Re:Is Robert Frost Even a Good Poet? by schiffern on Wednesday March 26, 2025 @04:07PM (#43486628)
It won't ignore it's training data (definitionally), but it will act like it's ignoring its training data, so in practice it's still a useful prompt engineering trick.
[ Parent | on HN ]