inari ( inari@piefed.zip ) to Programming@programming.devEnglish · 2 days agoI built a programming language that LLMs can't useblog.picheta.meexternal-linkmessage-square24linkfedilinkarrow-up158 cross-posted to: hackernews@lemmy.bestiver.se
arrow-up158external-linkI built a programming language that LLMs can't useblog.picheta.meinari ( inari@piefed.zip ) to Programming@programming.devEnglish · 2 days agomessage-square24linkfedilink cross-posted to: hackernews@lemmy.bestiver.se
minus-squareMirodir ( Mirodir@discuss.tchncs.de ) linkfedilinkarrow-up19·1 day agoAnd that’s without any of this being in its training set. I wonder if they realized how big of a self own that is.
minus-squarealdhissla ( aldhissla@beehaw.org ) linkfedilinkarrow-up8·1 day agoAs well-intentioned as this might be, I doubt they understand how trained models work.
minus-squareatzanteol ( atzanteol@sh.itjust.works ) linkfedilinkEnglisharrow-up1·1 day agoHow the hell is this a “self own”?
minus-squarealdhissla ( aldhissla@beehaw.org ) linkfedilinkarrow-up7·1 day agoThe premise was that this language is significantly different from other languages in terms of being understood and replicated by an LLM. The result showed that an LLM does exactly as well with it as you would expect.
And that’s without any of this being in its training set. I wonder if they realized how big of a self own that is.
As well-intentioned as this might be, I doubt they understand how trained models work.
How the hell is this a “self own”?
The premise was that this language is significantly different from other languages in terms of being understood and replicated by an LLM.
The result showed that an LLM does exactly as well with it as you would expect.