Sasha: Creative Goal-Oriented Reasoning in Smart Homes with Large Language Models · HackerPapers discussions

Sasha: Creative Goal-Oriented Reasoning in Smart Homes with Large Language Models — mentioned by evmaki

Sun, 14 Jan 2024 15:54:18 GMT

Awesome write-up - especially the fact that you've gotten it working with good performance locally. It certainly requires a little bit more hardware than your typical home assistant, but I think this will change over time :) I've been working on this problem in an academic setting for the past year or so [1]. We built a very similar system in a lab at UT Austin and did a user study (demo here https://youtu.be/ZX_sc_EloKU). We brought a bunch of different people in and had them interact with the LLM home assistant without any constraints on their command structure. We wanted to see how these…

Paper and discussion history. A mention is not an endorsement.

Sasha: Creative Goal-Oriented Reasoning in Smart Homes with Large Language Models — mentioned by evmaki

Sat, 20 May 2023 18:03:18 GMT

Super exciting to see the work happening in this area! I can especially appreciate the use of ChatGPT to orchestrate the necessary API calls, rather than relying on some kind of middleware to do it. I have been working in this area (LLMs for ubiquitous computing, more generally) for my PhD dissertation and have discovered some interesting quality issues when you dig deeper [0]. If you only have lights in your house, for instance, the GPT models will always use them in response to just about any command you give, then post-rationalize the answer. If I say "it's too chilly in here" in a house…

Paper and discussion history. A mention is not an endorsement.