[celdon25]

> We need llms to be able to tap that not add the same functionality a layer above and MUCH less efficiently.

Agents, tool-integrated reasoning, even chain of thought (limited, for some math) can address this.

[RagnarD]

You're both completely missing the point. It's important that an LLM be able to perform exact arithmetic reliably without a tool call. Of course the underlying hardware does so extremely rapidly, that's not the point.

[jdjdndnzn]

The computer ALREADY does do math reliably. You are missing the point.

[kruffalon]

Could you explain why that is?

[koolala]

A tool call is like 100,000,000x slower isnt it?

[kruffalon]

No idea really, but if it is speed related I would have thought that OP would have used faster rather than importance to try and make their point.

[koolala]

It's both. Being dirrctly a part of it makes it integrated into its intelligence for training and operation.