Love.Law.Robots. by Ang Hou Fu

Since receiving support requests and development ideas all over the place for redlines, I decided to try running a #Matrix room to centralise some discussion and an informal venue to ask weird and “stupid” questions. Since I am in the mood for experimentation, I wanted to run robots in my room. For my redlines room, I wanted a robot to track the activity on the GitHub repo, and welcome new users by posting what is the purpose of the room etc.

I was surprised to find very little documents or bots on how to run a matrix bot. I decided to go with maubot because I like the idea of plugins. While the interface and the docs leaves something to be desired, it’s actually relatively straightforward. Here’s a short write-up/#tutorial of how I did it in case it helps someone out there.

Should I submit this as a talk to #geekcampsg? ⊕I originally reserved this for Tech.Law.Fest, but chickened out when I was not sure there was an opportunity to speak. (On hindsight, my hunch was probably right.)I am thinking about lots of things: is this an interesting topic to share, is it a 5-10 mins or 30-45 mins presentation? While I continue procrastinating on taking the plunge, I thought I would outline the topic here for future reference. Feel free to let me know of your comments!

I’ve been kinda hot and cold on Retrieval Augmented Generation (RAG).

I rushed in and experimented early using an overview of Singapore law. After seeing other locals try to implement them, I scoffed at it. I dismissed it as “grab three relevant articles from my vector db and ask #ChatGPT to write an answer on it”. Now I am going to have a second go.

I used to think #chatbots are lame. You type stuff in and pray the “AI” understood what you said. If you knew what you want, you’re not going to ask nicely. Just give me a button or a dropdown!

With #GenAI like #ChatGPT, the odds of hitting the mark with your program have improved. I explored making a legal chatbot early on but I hit a dead-end when I couldn’t figure out what the use case is.

Even if I did figure out a use case, the next problem if I wanted to take it to the next level is pricing. How do you charge someone for using your legal chatbot?

I saw this post the other day that got me thinking about how I learnt to #code.

There was a tweet yesterday about how major python libraries mostly aren't written in python, and it implied that this was something that should be fixed. I take it as revealed preference: experts don't like working in python. It's also a terrible language for beginners. pic.twitter.com/wBVJDNPCiJ

— David Mimno (@dmimno) July 13, 2023

It was a great opportunity for me to revisit a post I wrote nearly a year ago on the subject: So you want to code? (Lawyer Edition)

Watching large language models spew words at each other hasn't improved my understanding of them.

Houfu dreams of having his #MachineLearning tool for years but will still have to wait longer.

I attended a roundtable organised by the #Singapore Academy of Law titled “Generative AI and the Impact on Law and Society”. Although they weren't able to end the seminar without talking about misinformation, I was glad that the technical detail (both on the engineering and legal level) were more advanced. I even heard the word of a Legal #GPT trained on the datasets of local legal materials.

Large language models like #ChatGPT present a unique opportunity to train #lawyers in new ways. I discuss a simple courtroom #simulator I created that is able to mimic the cuts and thrusts of advocacy, and wonder whether anyone will use it.