Comment by coldtea
1 day ago
>Oh give me a break. Show me one example of 1) any knob twisting that makes the underlying model better.
I mentioned several.
You're now once again changing goalpoasts to say you meant the underlying model, not the overall llm performance, even though you explicitly wrote: "Their performance depends solely on the model training before release and how well you curate the context you feed it".
So, the context curation was relevant (meaning you didn't constrain your claim to the underlying model), but now somehow all the additional tunables aren't relevant (because suddenly you're just talking about the model).
End of discussion.
None of what you mentioned changes the model. Because it's a fixed model. The weights are constant. It does not learn. It only knows what gets repeatedly fed to it and those fixed relationships represented by the weights. You can pretend like that's not true, but unfortunately for VCs it is true.
End of discussion.
"Their performance depends solely on the model training before release and how well you curate the context you feed it".
Wrong. The face-saving backtracking doesn't change that.
The models do not get better until a new one is released. And we are already at diminishing returns. So sorry. Also sorry you don't know the difference between a model and a context, harness, router, or cache.