 Notice. New forum software under development. It's going to miss a few functions and look a bit ugly for a while, but I'm working on it full time now as the old forum was too unstable. Couple days, all good. If you notice any issues, please contact me. |
Forum Index : Microcontroller and PC projects : Building games with AI - something about the process
| Author | Message | ||||
| matherp Guru  Joined: 11/12/2012 Location: United KingdomPosts: 11856 |
Obviously, I'm not writing all the games myself and Claude is doing a lot of the work but I thought it might be interesting to outline the process I'm using. I'm working in VSCode and everything is held both locally and then committed and pushed to github. First, I need a game where there is source code of whatever type out there and this is the case for many of the seminal BBC Micro games. Next, I tell the AI that I am thinking of implementing game AAAA and to review the Game Development Guide pdf and any other docs that might be relevant (3d-Graphics manual for Elite). I've also set up a file of MMBasic key rules that it is told to review e.g. A=A!=A$=A%, variable scope, case insensitive, avoiding reserved words and the AI is told to reference this before anything else. The next step is to ask it, without coding anything to conduct a design review of how to build the application. For examples of these have a look at: https://uktailwind.github.io/AI-design-files/Exile_Port_Design_Review.html https://uktailwind.github.io/AI-design-files/Elite_Port_Plan.html https://uktailwind.github.io/AI-design-files/Thust_Port_Plan.html If you do nothing else look at the exile file for a real understanding of the current power of AI. These typically have numerous questions in the first instance and this is where my knowledge of the inner workings of MMBasic come in as I can tell the AI the option to choose or alternatively propose a test environment to get to the best approach. Typically there will be numerous test programs written to tease out the best way forward and these are run on the real H/W. The design guide gets updated as each decision is finalised and you can see this in the versions posted. Next I will get the AI to start going through the recommended phases. I will have a PC3 connected to a com port that the AI can access and it has scripts for xmodeming code onto and off the board and I have coached it in capturing screen images to analyse for correctness. My role is to identify bugs and issues and feed them in and, most importantly, stop it going down rabbit holes which it has a serious tendency to do. Often, it will hit roadblocks and this is when my knowledge of MMbasic comes in to get it to understand why it is seeing an issue and to coach it into the correct approach. It is an iterative process between me and the AI and although it can code much faster and more accurately than me I'm still very confident in my intellectual advantage in architecting, overseeing, problem solving and phasing in the build. Net result is that Elite took about 16 hours of my time and I don't suppose there was any period of more than 3 or 4 minutes when I wasn't interacting with the AI to work with it to develop the final product. Basically, This is exactly the job I was doing way back developing major applications with a team of 20 programmers Edited 2026-09-15 23:40 by matherp |
||||
v.lenzer Senior Member  Joined: 04/05/2024 Location: GermanyPosts: 155 |
Hi Peter! Thanks a lot for this in-depth look at your workflow with AI. Do you get the impression that, from one project to the next, the AI has a better understanding of what you want from it—meaning it doesn't just correct itself but actually learns? And could it be that one day you’ll only have to say, "Port this program to MMBasic for this or that firmware"? Best wishes! Joachim |
||||
| matherp Guru Joined: 11/12/2012 Location: United KingdomPosts: 11856 |
Sort of, but not consistently. When developing something big huge context is built up but that holds tokens and is largely lost at the end (and when the AI compacts). I now get it to note all key things as development notes and to some extent these are read in a new session but not all. This is part of my "job" to get the AI to reference all the various relevant knowledge before starting something new. |
||||
Bryan1 Guru Joined: 22/02/2006 Location: AustraliaPosts: 2261 |
Peter I do feel your pain when claude decides to go down it's rabbit hole after 2 months of working on club.py last night was the car club meeting where I didn't go as claude had managed to brick board 1 with the 10" lcd, board 3 where it sat in an endless loop all day trying to connect to GPS. Now Monday morning I setup that 48 port network switch and Cisco wifi router where it worked nicely so told claude don't bother with serial anymore as it is too flakey and just use the wifi to transfer the files. Well it did work and pretty well instant too so I did think we were on a winner. Now I did ask for a ram gauge to go in the ticker so I can see just how the pico3 is going when running and found just sitting on the menu page around 60% of the ram was used so this was the major problem with BT. We finally worked out where the problem was when SQLLite was engaged it was setup for 1,000 members and taking over 1/2 of the ram just to run. Anyway come Tuesday and all memory of using wifi to transfer files was gone and when the Cisco wifi router used a .4 subset claude went into meltdown saying it was a hardware fault and refusing basic 101 networking to fix the problem. Computer B where it has HDMI input is good for running the code and with networking setup ssh is used now on Monday it setup the wifi on B but didnt set it to start on boot and had no memory of ever doing it. So after asking like 20 times it finally got on and setup wifi on B then that .4 subset was gone but the major problem claude with its rabbit hole decided board 2 as it was on serial was board 3 and kept programming that instead of board 3. Well the last straw yesterday as board 2 had all the new code lets try BT again only to find when clicking music straight back to the login page. Regards Bryan |
||||
TassyJim Guru Joined: 07/08/2011 Location: AustraliaPosts: 6604 |
Thank you for demonstrating the work required to get AI to produce usable outcomes. Otherwise, you can get dangerous results: In Tasmania, a prisoner was released early and a condition of her parole was she couldn’t talk to the media. She contested this condition in the Supreme Court and won. The reason why she won was because the Parole Board used AI to help write their submission. AI referred to historical cases and decided to “invent” some of its own. The media are calling it “AI Hallucinations” Less important but still wrong: When I do a Google search, its AI often replies with BS. It ignores the data sheets and instead refers to Facebook etc Ask Google “how many countries are there in the southern hemisphere?” Googles AI replies 33 The first website listed after the AI blurb lists 43 countries by name. They do agree that there are 13 straddling the equator I'm not ready to put in the time to learn how to control AI. Hell! I can't even train my dog to come to have his feet wiped. Jim VK7JH MMedit |
||||
Revlac Guru Joined: 31/12/2016 Location: AustraliaPosts: 1305 |
"Building games with AI" Quite interesting, Thanks Yes I had thought of starting a thread about Google AI And its misleading searches), or maybe someone will soon, its far more problematic than it first looks, Thanks for sharing.  Cheers Aaron Off The Grid |
||||
 Print this page |
 |
The Back Shed's forum code is written, and hosted, in Australia. | © JAQ Software 2026 |
