Comment on My thousand dollar iPhone can't do math
panda_abyss@lemmy.ca 15 hours agoYea, but those are all using heaps of proprietary heuristics.
The beauty of LLMs and one of their most useful tasks is taking unstructured natural language content and converting it into structured machine readable content.
The core transformer architecture was original designed for translation, and this is basically just a subset of translation.
This is basically an optimal use case for LLMs.
MolochHorridus@lemmy.ml 15 hours ago
Quite obviously not the optimal use case. “The tensor outputs on the 16 show numerical values an order of magnitude wrong.”
JPAKx4@piefed.blahaj.zone 11 hours ago
That’s the hardware issue he was talking about, it has no relation to the effectiveness of the usage of the LLM. It sounded to be mostly a project he was doing for fun rather then out of necessity
db2@lemmy.world 14 hours ago
Grok says it’s right so it must be 🤤