Hacker News Reader

Comment by MuffinFlavored | Hacker News Reader

> don’t you think OpenAI would’ve worked on something like this?

Along this line of thought: was it a massive oversight for them to not train the model to say "math detected, let me pass that to a solver" instead of trying to guess what token should come next in a math problem?

View on HN

There's a million categories of problem you could ask an LLM to try to solve. You'd need a million solvers…

This seems like a pretty good thing. The model’s ability to detect _which_ solver to use is the killer feature.

Why is that a killer feature? Humans are quite good at asking different people different questions. If I need to do a simple math problem I'll just prefix "calculate" and pop it into Google, whereas if I want an intro to a named thing I'll prefix "wikipedia". That's not hard.

GPT is quite useful, but not because it solves the problem of "I don't know where the question I have is answerable by a calculator"

you mean huggingGPT?

If you used some sort of plugin system, you could just make a solver for your specific task and drop it in. Doesn't ChatGPT Plus do this now?

It's behind a waitlist.

OpenAI plugins can connect with a growing number of things. Zapier is one, which is already several thousand functions.

Can you give some example recipes?

Most obvious one is Wolfram, it passes most math to Wolfram

They are solving that with plugins now.

Reply on news.ycombinator.com