Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

TypeChat

microsoft.github.io

Post reply on HN
Print view View original

1–10 of 174 posts

Re: TypeChat

#2

Post by davrous »

This is a fantastic concept! It's going to be super useful to map users' intent to API / code in a super reliable way.

Re: TypeChat

#3

Post by paxys »

I swear I think of something and Anders Hejlsberg builds it.

Structured requests and responses are 100% the next evolution of LLMs. People are already getting tired of chatbots. Being able to plug in any backend without worrying about text parsing and prompts will be amazing.

Re: TypeChat

#4

Post by joefreeman »

> It's unfortunately easy to get a response that includes { "name": "grande latte" }

    type Item = {
        name: string;
        ...
        size?: string;
I'm not really following how this would avoid `name: "grande latte"`?

But then the example response:

    "size": 16
> This is pretty great!

Is it? It's not even returning the type being asked for?

I'm guessing this is more of a typo in the example, because otherwise this seems cool.

Re: TypeChat

#5

Post by mynameisvlad »

joefreeman wrote: post #4

> It's unfortunately easy to get a response that includes { "name": "grande latte" } type Item = { name: string; ... size?: string; I'm not really following how this would avoid `name: "grande latte"`? But then the example response: "size": 16 > This is pretty great! Is it? It's not even returning the type being asked for? I'm guessing this is more of a typo in the example, because otherwise this seems cool.

I feel like that's just a documentation bug. I'm guessing they changed from number of ounces to canonical size late in the drafting of the announcement and forgot to change the output value to match.

There would be no way for a system to map "grande" to 16 based on the code provided, and 16 does not seem to be used anywhere else.

Re: TypeChat

#6

Post by ameyab »

Here's a relevant paper that folks may find interesting: Semantic Interpreter leverages an Analysis-Retrieval prompt construction method with LLMs for program synthesis, translating natural language user utterances to ODSL programs that can be transpiled to application APIs and then executed.

https://arxiv.org/abs/2306.03460

Re: TypeChat

#8

Post by trafnar »

It's not clear to me how they ensure the responses will be valid JSON, are they just asking for it, then parsing the result with error checking?

Re: TypeChat

#9

Post by hirsin »

joefreeman wrote: post #4

> It's unfortunately easy to get a response that includes { "name": "grande latte" } type Item = { name: string; ... size?: string; I'm not really following how this would avoid `name: "grande latte"`? But then the example response: "size": 16 > This is pretty great! Is it? It's not even returning the type being asked for? I'm guessing this is more of a typo in the example, because otherwise this seems cool.

The rest of the paragraph discusses "what happens when it ignores type?", so I think that's where they were going with that?
Post reply on HN