Scott @twoc.bsky.social · 14/10/2026It took a lot more effort and using Google AI to get this working like I wanted, but now it looks great! The preview can be placed in the center and expanded as much as I want. I removed the file list tab too. This will be good for reading markdown files on stream. 🤓😎👍 000
Scott @twoc.bsky.social · 14/10/2026(it worked) But wait, there's more 😄🤖 KDE Craft appears to be installing too. Then getting that custom Ghostwriter compiled (if it works) 000
Scott @twoc.bsky.social · 14/10/2026Microsoft effectively paywalling an old version of Visual Studio Community Edition. Well... Thanks Google AI! 🤣 The command to install: winget install Microsoft.VisualStudio.2022.BuildTools --override "--passive --add Microsoft.VisualStudio.Workload.VCTools --includeRecommended" 100
Scott @twoc.bsky.social · 14/10/2026I'll use whatever free tier compute I can. 🤣 (it's actually good to burn the compute of these cloud things so they get the picture we want affordable hardware again to do local AI assisted programming. Trying to mod Ghostwriter so I can get the panel layout I want. 🤖🔍(lol, it didn't last long) 010
Scott @twoc.bsky.social · 12/10/2026I don't want to support the idea of programming as a service, but I will use free tier tools (and local models as much as possible). We are inching toward that Star Trek TNG future of programming as a process of language and logic you give rather directly implementing the solution yourself. 200
Scott @twoc.bsky.social · 10/10/2026Hopefully that works because AI Studio has issues sharing "chats" with a lot of files. For the current project I'm working on it's a bit over 1MB of text. 😄 (so far it is, so a lot simpler to make a new chat window for each issue or change) 000
Scott @twoc.bsky.social · 30/08/2026Computers & technology are cool. I wanted a complete list of products covered on my drink/snack review channel so I can avoid duplicates in the future. Gemini Pro in AI studio with some direction made an API access script with my suggestion for local Gemma-4 to understand titles/descriptions. 🤓🤖 211
Scott @twoc.bsky.social · 10/07/2026Using these systems is kinda funny. Copilot with free tier Claude didn't code it properly. Seeing of Gemini 3.1 Pro can fix it. 🤣👏 010
Scott @twoc.bsky.social · 10/07/2026Got it running again. Copilot was writing script commands into the solution file. 😅 000
Scott @twoc.bsky.social · 10/07/2026Having multiple AI work on getting a console log control to stop scrolling when the user scrolled up is apparently an extremely difficult task. 😅😄🤷 used up the monthly Kiro credits and now having Copilot try to finish the task. 🤖🤖 400
Scott @twoc.bsky.social · 04/07/2026I wanted to move embedded YouTube videos in website articles down to the bottom of each article. Another easy project by using Gemini Pro to make it. A few checks to verify and had it process all of the websites. I'd eventually like to reprocess affiliate links to fix old ones. 🤓 000
Scott @twoc.bsky.social · 25/05/2026I'm by no means a domain expert in this stuff, so my "job" is trying to give it the knowledge I'm able to collect and simple logical guidance. I can also research things in the moment, but yeah. 🤓🤖 000
Scott @twoc.bsky.social · 25/05/2026That compute didn't last long. Also, it isn't very smart. It failed at multiple attempts to fix something it made. 000
Scott @twoc.bsky.social · 25/05/2026This is pretty good so far. We'll see how long the free tier compute holds out. 000
Scott @twoc.bsky.social · 25/05/2026I'm trying yet another agentic programming IDE. 🤖😄 Every free tier I can find to get the job done without having to resort to hand-coding. 👏 200
Scott @twoc.bsky.social · 24/05/2026I'm working toward trying to make an ACDSee Photo Studio plugin that does automatic white balance and exposure (highlight & shadows adjustments also welcome). I made two XMP files with the range of sliders in the Develop tab so I can avoid data issues. 000
Scott @twoc.bsky.social · 21/05/2026Past 3am, getting correct XMP/sidecar/develop settings has been difficult. Even the most advanced AI I have access to needed direction. I've got it applying changes now, but it needs a lot of work. Especially with white balance calculation. Also, there are still problems applying changes. 100
Scott @twoc.bsky.social · 18/05/2026Turns out my use of llama.cpp had issues I wasn't paying attention to with the command. It looks like tokens per second jumped from like 15/s to 100/sec. 000
Scott @twoc.bsky.social · 18/05/2026I've got a bunch of convention photos to edit, but it's all practical RAW image edits. ~7 months ago I did some initial research on Acdsee plug-ins. Right now I starting the initial project, but ran out of credits on the cloud models. Seeing if my local option can finish the work. 100
Scott @twoc.bsky.social · 15/05/2026Another quick programming project (that Copilot AI wrote based on my design document and some refinement/fixing up afterward). Finding projects in my project drive that are finished based on if there are horizontally formatted mp4s in a Renders folder. 🤓🤖 000
Scott @twoc.bsky.social · 14/05/2026Wow, it is actually working as far as I can tell. The task I gave it was pretty simple but it figured it out and wrote the code properly! 🤖😎 It wasn't fast but it also wasn't crazy slow, so maybe I might be able to use it in a pinch. But I still want to try with smaller models. 000
Scott @twoc.bsky.social · 14/05/2026This might be working now. Gemini Pro created a go-between of sorts to take the breaking messages from VS Copilot and feed it to the local model in ways that it can handle. This prompt ran at least! It's slow on my PC so not especially useful, but I'll try it with a smaller model out of curiosity. 100
Scott @twoc.bsky.social · 14/05/2026I used Copilot (Claude 4.5 mostly & a bit of GPT) to make it. Now I'm using Kiro to fix up the comments that Copilot didn't bother adding. I have it set to auto mode, so not sure which model that one is using. Ideally this level of usefulness would be viable locally at some point. 000
Scott @twoc.bsky.social · 14/05/2026A few minutes writing up a design document to make an application that transfers video renders from where I put them back into their respective project folders. This should save a lot of time because I had done it by hand. I had 80 or so renders sitting waiting to be transferred, EZ! 🤖😎 100
Scott @twoc.bsky.social · 13/05/2026kind of works but too slow and probably not smart enough. It's been minutes of "Look over the code and see if you can find any functions that are missing a /// type xml comment at the top that describes what a given function does...." 000
Scott @twoc.bsky.social · 13/05/2026Now it's trying to make its own server to go between the two instead of using LiteLLM because that wasn't following instructions. 😅🤖 000
Scott @twoc.bsky.social · 13/05/2026Another branching path, using LiteLLM as a go-between. We'll see if it works! 000
Scott @twoc.bsky.social · 13/05/2026A ton of changes and trying different commands Google AI suggested later, it's giving me a response. I also switched to the MoE Qwen 3.6 instead of the standard one. The lack of VRAM is rough and this one is faster at least. Trying to push it to see if it sends a failure response to VS Copilot. 400
Scott @twoc.bsky.social · 13/05/2026Trying out Qwen,3.6 27B 4-bit on my hardware. It's slow but it runs. If I had a GPU with 32GB of VRAM it might be usable. The AMD Radeon AI PRO R9700 is around $1400 and the Intel B70 is $1100 but not sure on support of either. 100
Scott @twoc.bsky.social · 03/05/2026I'm impressed with the state of AI assisted programming. It's come a long way since trying to use the original ChatGPT to this Kino program basically turning into and advanced worker I direct and help guide toward solutions it usually finds and implements. 000
Scott @twoc.bsky.social · 02/05/2026Been trying out Kiro. A friendly chatter stopped by a stream recently and suggested it. They apparently work at Amazon, so not surprised they use it. Good dev talk & they even gave some bits which probably the first time I've gotten any. 😺 So far Kiro is pretty cool as a supplemental IDE. 100
Scott @twoc.bsky.social · 21/04/2026Had a breakthrough getting dock-able "Custom Command" scripts working with Vegas Pro. 🤓 000
Scott @twoc.bsky.social · 21/04/2026🤔 This Nemotron Cascade 2:30b seems to be running okay on my PC with its meager RTX 4060 8GB GPU. The CPU is an AMD 9900x and 64GB of VRAM. Slow part is the initial start. 000
Scott @twoc.bsky.social · 21/04/2026I'm trying to implement a dockable window in Vegas Pro, but there are a lot of technical challenges. Though I'm not sure if it's Gemini Pro failing at understanding how to edit video on the timeline or some other issue/bug. Giving Copilot with Claude a chance to see what it can do. 010
Scott @twoc.bsky.social · 17/04/2026I'm working on a big project that is a successor to my Vegas Pro video editor scripts. In this case I'm taking things a step further to manage video projects from start to finish. Hopefully with a lot of features that facilitate producing work faster while keeping it high quality. 110