I’ve been thinking, for a while now, how I could merge a LLM and an Expert System. What I wanted was the ease of use of an LLM and the rules based processing of an Expert System. Over the past couple of weeks, I built what I thought was a unique way of merging the two. I choose to use auto insurance as an example because of my past history in the industry, but I feel as though it would be applicable in other industries. It’s still very rough around the edges, but if you are interested you can try it out at https://mktbx.com/#tryout I’d appreciate any feedback and your thoughts.
I have a couple. A fun one is catchingkillers.com. Here you are a private investigator who is trying to find out who committed a murder. Two stories are active. The third, bathtub one, isn't done.
Yeah I did just that. CatchingKillers.com hosts the game. The first two stories are playable. Sour Grapes of Wrath, taken from an excellent pdf I found online. The other, The Masquerade Murder of Charleston Manor, is custom story for the game. The third story hasn't been finsihed. So not really payable. I have set the limit on that gpt account to $5 so I don't get abused, but should be enough for a bunch of runs of the games if someone wants to try.
I built out a few utilities as experiments. One app linked to Salesforce to query/analyze sales data. Another that reads our help documentation and gives instructions via chat.
The last app, the only one that was deployed anywhere, is https://catchingkillers.com This app is a simple murder mystery game where the witnesses and the killer are ChatGPT bots. The first two stories are complete and active, the third is not complete yet. The first story of the working two is taken from another murder mystery group game https://www.whodunitmysteries.com/sour.html. The second story was highly influenced by ChatGPT.
It's a bit rough because I didn't spend too much time on it, but if anyone does signup to play, I'd love to hear feedback.
I've tried something similar with a little side project, https://catchingkillers.com. The witnesses, chatgpt chat bots, wouldn't have much of an attention span and start making things up. I think this added to the fun of the game. You had to question each witness to get verification on what another chat bot said.
Not sure if it's the best but I recently bought a "Airthings 2960 View Plus - Radon & Air Quality Monitor". Choosing the correct app and setup was a bit annoying, but not too bad. I think setup was about an hour once done. Also the phone app wanted to read results for a week or so before displaying some info. The device has a screen that will show you the current values.
I purchased the device because I was a bit worried about radon and other garbage that I might be breathing while working in my basement office. Radon and other data points were not a problem. Turns out C02 was more my problem. It's pretty surprising how quickly that number rises with a closed door. I believe I can attribute the tiredness with the C02 levels. Having history correlates with when I'm in the basement office, and opening a window, it's a walkout basement and I have windows, decreases C02 stat pretty quickly.
Overall I'm happy with my purchase, and I'm considering buying another one for the ground level of the house.
On the Home Performance channel on YouTube, the AirThings View Plus is the top model recommended by Corbett. And you see it in his own home. It's one of the only devices I've been able to find that can do PM2.5 as well as CO2 and also Radon.
I've made a bunch of projects that hit about 80% completion that I never end up finishing. My current projects that I have most recently put in some time are:
https://cruisedirector.io/ I have it running on some of my sites. It continues to run but I have no customers, and I haven't tried to sell it as a service. Tracks user actions inside an application. Every click is tracked so you can make rules based on any user clicks and show prompts made with a graphical editor. For example: Someone is button smashing, you can ask them for feedback. Popup a message on first login in the past month... Really lots of fun stuff.
https://ezdataloader.com/ I recompiled some old c# code from about 10 years ago, and with a few tweeks the backend now can run in mac, windows, or linux. Pretty sweet, other than the interface. I used electron for an interface and got it working a bit. But, I haven't put too much time into this one either. I'm tempted to scrap the downloadable executable, and turn it into a saas app. Might be a bit easier for customers I'm targeting. I've been pretty busy at my day job though, and haven't had time for this in the past year or so.
Just as another point of reference. I followed the windows install. I'm running this on my 1060 with 6GB memory. With no setting changes takes about 10 seconds to generate an image. I often run with sampling steps up to 50 and that takes about 40 seconds to generate an image.
