I'm tinkering much more because I have an easy way to enter into a new domain and apply what I know to that domain. I can also get unstuck a bit more quickly as I go deeper. Before it was reading textbooks, this turned into searching the web, now I have a minion who can go write me a summary. Is the minion perfect? No, but more often it is.

Same, but with vision models. Unfortunately, I might be at my limit locally. I have three models that I'm using to find and identify objects in pictures. The largest dataset and model now takes about 8 hours per epoch on my Mac M4 with 16G memory.

Yeah this was what got me to start doing short rentals of bigger gpus in the clouds, upload your parquet files and it takes a couple of hours for a thing that would have my mac at 100% for a couple of days

I’ve been continuing work on https://mybulkcards.com, a phone app and website for scanning, organizing, and searching Pokémon card collections, especially the thousands of bulk cards that my daughter and I have in our closet from playing.

The goal hasn't changed too much, make building decks easier by knowing exactly what you own and where it’s stored. You organize cards into boxes, search your inventory, search friends’ collections, and keep track of trades instead of digging through a similar closet of cards that my daughter and I search for.

The fun part has been the AI. I trained computer vision models that run entirely on the phone to detect and identify Pokémon cards. Training has become the slowest part. For the model that needs to be retrained every new release, I’m up to about 5 hours per epoch on my M4 Mac with 16 GB of RAM.

The Android app is currently in public testing with people from my local Pokémon league. It’s built with React Native, and I’m working on the iPhone version next.

Still lots to build, mostly around product and ux, and because a recent stupid mistake on my part, backups and deployment safeguards.

I would love this for magic the gathering

The app and scanner is heavily inspired by Manabox. It's a great product, and I would have used that if they did Pokémon, but it's only Magic.

I’ve continued to work on a phone app + website (https://MyBulkCards.com) to scan Pokemon bulk cards and tag/organize where they are stored. I added a bunch more features like finding a friend, searching through friends cards, and trading.

It's been pretty fun to build. Trained a couple of models to identify a card that run on the phone app. They work very well and are comparable, and much better than many, to any other card identifier in the market. As the models get more complicated training is getting a bit longer. I'm at about 9 hours per epoch on my Mac M4 with 16G of memory.

The Android phone app is in public test with a couple of my local group testing. The app is built in React Native, and I’m hoping to get an iPhone version out soon since there are a bunch of iPhone peeps.

I've continued working on a tool for my daughter, our friends, and I to scan and index Pokemon cards. The tool is a phone app and website (https://MyBulkCards.com) The phone app uses the camera to scan a card and run the image through a couple of models, a record is written of the card along with the location. It's pretty basic, but I can store cards in boxes like “Box 1 AAA, Box 1 BBB, …” and find cards easy peasy. There’s also a friends feature so I can see what others have locally. We borrow cards from each other quite a bit.

It's been a super fun tool to build. The phone app just got approved in the Android app store. I have a bit of cleanup, but plan on releasing it soon.

My daughter introduced me to Pokémon TCG. We found a local group and have been playing for about a year and a half. At this point we have so many bulk cards that it takes way too long to search through them. Other than a few specific pulls we keep in a binder, we honestly have no idea what we own.

I’ve been building a phone app + website (https://MyBulkCards.com) to scan cards and organize where everything is. It’s pretty basic right now, but I can store cards in boxes like “Box 1 AAA, Box 1 BBB, …” and find cards easy peasy. There’s also a friends feature so I can see what others have locally. We borrow cards from each other quite a bit.

It’s been a fun project to build. I trained one model to find a card in the camera frame and another to identify it. Still iterating a lot. One epoch on my Mac M4 takes about 2 hours, and I’m still seeing improvements past epoch 10. Even now, it can find and identify a card more often than not, even without the OCR bits. Both models are under 20MB, run directly in the camera frame, and are fast enough to identify a card as I slide it into view.

I started with Android since that’s what I have, and I’ve shared the app store testing link with my local group for testing. The app is built in React Native, and I’m hoping to get an iPhone version out soon since there are a bunch of iPhone peeps. A couple of the players also got me into MTG, so now I’ve got a pile of Turtles cards too. I’ll be training an MTG model next. I don’t think it’ll be too bad since I can reuse most of the same approach.

Haha! I did something similar, and went as far as integrating a label printer (ZQ620) and use a TC53 with the barcode scanner to sub organize quickly :x.

I started working on https://billsimplified.com/ an easy to use billing solution that can help me collect taxes and run dunning.

Hey HN,

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.