News for hackers. Stuff that matters.
Re:Field Experimental Evidence of AI on Knowledge Worker Pro... by Fin_Code on Tuesday January 16, 2024 @12:51PM (#39016306)
This is entirely unsurprising. A language generator is not designed for analytical analysis. The fact it codes well is what I think is throwing people. Since code is a form of language it works well for the language model. The issue with code will come from larger context where analytical thought is needed and it will break down.
Re:Field Experimental Evidence of AI on Knowledge Worker Pro... by svachalek on Tuesday January 16, 2024 @04:05PM (#39019128)
People are trying really hard to make "search" or something like it the killer app for LLMs but from what I've seen, it's translation. Coding in its purest form is a kind of translation, from natural language requirements to more precise computer languages and vice versa. Keeping an LLM properly focused on that task, it's pretty astonishing what it can do. But as you say, assuming it can do anything more than that is a trap.
Re:Field Experimental Evidence of AI on Knowledge Worker Pro... by chewxy on Tuesday January 16, 2024 @05:40PM (#39020153)
> Coding in its purest form is a kind of translation, from natural language requirements to more precise computer languages

Unfortunately not so true. A simple way to check this is to look at what the brain is doing. Coding barely triggers the language components of the brain (your usual suspects like the Vernicke's and Broca's areas + other miscelleneous things). In fact what you'll find is that coding triggers the IP1, IP2 and AVI pathways. These are part of the multiple demand network. We call them programming "languages" because we can represent them in a token-based game we call "language" but the act of programming is far from mere language manipulation.

Re:Field Experimental Evidence of AI on Knowledge Worker Pro... by nomel on Tuesday January 16, 2024 @08:08PM (#39021710)
> from natural language requirements to more precise computer languages

This makes sense. Translation to precise code would include more of the logic/planning bits of the brain, since that's the context of the output. I suspect a person fluent in Lojban[1] would show similar areas activating during translation from English to Lojban. I also assume translating code to words, with documentation, would include more language, since that's the context of the result.

That doesn't mean it's not translation. It's just translation to a precise description of intent.

1. https://en.wikipedia.org/wiki/Lojban