←back to thread

222 points futurisold | 1 comments | | HN request time: 0.219s | source
Show context
jaehong747 ◴[] No.44400917[source]
great job! it reminds me genaiscript. https://microsoft.github.io/genaiscript/

// read files

const file = await workspace.readText("data.txt");

// include the file

content in the prompt in a context-friendly way def("DATA", file);

// the task

$`Analyze DATA and extract data in JSON in data.json.`;

replies(2): >>44400961 #>>44401179 #
futurisold ◴[] No.44400961[source]
Thank you! I'm not familiar with that project, will take a look
replies(1): >>44401187 #
krackers ◴[] No.44401187[source]
Some of this seems a bit related to Wolfram Mathematica's natural language capabilities.

https://reference.wolfram.com/language/guide/FreeFormAndExte...

It can (in theory) do very similar things, where natural-language input is a first class citizen of the language and can operate on other objects. The whole thing came out almost a decade before LLMs, I'm surprised that they haven't revamped it to make it really shine.

replies(2): >>44401224 #>>44401230 #
1. futurisold ◴[] No.44401224[source]
> I'm surprised that they haven't revamped it

No worries! I can't find it right now, but Wolfram had a stream (or short?) where he introduced "Function". We liked it so much we implemented it after one day. Usage: https://github.com/ExtensityAI/symbolicai/blob/main/tests/en...