The Chinese models are being released as open weight models, which are what people who want to run these systems locally are using. By banning them this just means that in the US only corporate models will be available to anyone.
It means that data centers will just find a way to have themselves classified as anything except for a data center... meanwhile anyone who happens to have more than 3 computers in their homes will have to pay extra on their electric bills.
Except that it isn't. There are many open AI models being created by non-corporate entities, NousResearch is one of the more popular ones. They are dedicated to creating open models for the betterment of all.
And even if you do use open models that were created by a corporation... ok. It isn't like using those models on your own hardware, on your own network, is going to be providing anything to those corporations.
To be fair, Google had the ability many years before ChatGPT was released to release a similar product but they purposefully didn't, and instead they only used it internally. And then when OpenAI did their release Google was one of the voices calling for moderation. They released Bard because otherwise they were going to be left behind, and likely have lawsuits from investors.
I have my local LLM currently setup and it runs just as well as Sonnet 4.6 from a quality standpoint, and for performance it is slightly slower but it's still faster than I can respond.
This is with a Strix Halo APU with 128GB unified memory using the latest Qwen3.6 models with llama.cpp.
My favorite Scrabble win was using 'eBay'... before playing that word I looked at the instruction sheet and it specifically said that "words that begin with a capital" are not allowed. There were some sour grapes after that one.
This is how we play... and it has resulted in some VERY long games.
Once we had some friends over and their 8 year old son was playing with us. He almost won a few times, but his dad did everything in his power to keep him from winning. It was close to midnight before that game ended and it was the first time I considered changing the house rules.
Which Zahn books? The Heir to the Empire or the newer Thrawn trilogy? I love both, and I feel like they've done an incredible job with Rebels, Ahsoka, Mandalorian... really all of the tv shows (though I haven't watched Maul yet). I would love for them to continue telling these stories and have the original characters just show up where it makes sense... like Luke coming to collect Grogu for training. Maybe have Han and Chewy running a cantina left to him by Lando. Ewoks starting the process of joining the New Republic and electing representatives. And Wedge... well, he had enough of war and no one has heard from him in many years.
They don't need to keep telling stories about Luke... the remarkable part of his life happened when he was young, now he's doing the boring and difficult work of rebuilding the Jedi Order. There's no exciting story there, but he can be in the background of other characters who are doing remarkable things.
Last night I decided to try Little-Coder to work on a game that I've had in the 'plannng' phase for a while. I had a few issues getting Little-Coder to work with my system, but once it was working I pointed it to the project fact sheet in my Obsidian vault and told it to get familiar with the project and ask any questions. It had a few questions and then wanted to know if I wanted it to get started on a prototype for the gameplay. The game is a narrative driven politics game and I asked it to create the prototype as a brower game. It ran for about 40 minutes and then had the working prototype. There were a couple of bugs with some buttons not working, but those were easy to fix.
This is really impressive. I'm making this game for my daughter and I let her play the prototype (which is very repetitive at this point since the 'narrative' hasn't really been written yet) and she loved it. She played it for about 15 minutes before realizing that it had started repeating. I've been working on the game all day today and she came in a bit ago and asked when she can play again.
And thanks for that video on Qwen3.6 27 dense... I might have to throw my system at it and see how it handles things.
I did some analysis on OpenCode, Little Coder, Aider, OpenClaude and ClawCode and each one had potential issues with my specific setup (OpenCode and OpenClaude have a looping bug at the moment, Little Coder is brand new and has potential, but I'm leary of new projects, Aider is promising but had some unknowns)... anyway, as I was evaluating these I realized that I currently use Claude Code, all I have to do is use that with my model rather than using their models. A few quick changes and now I have Qwen3.6 in Claude Code. I asked it to create a web-based Tetris game... 7m13s later I have a fully functional, minimally buggy Tetris game in my browser!
I was trying that with Coder-Next but it would often just ignore those instructions. I didn't change any of my instructions when I moved to Qwen3.6 and it has been following them solidly.
I hadn't heard of OcuLink before the Framework event yesterday... and now I'm intrigued. How does that connect to the Framework Desktop?
And as far as tools go, I tend to borrow ideas from others and then build them specific for my setup. For instance, a few months ago I came across a project called OpenBrain that uses a vector database for memory storage and retrieval. I leaned on Claude and asked it to evaluate the OpenBrain project and to let me know how we could use the concepts for my local system. Claude chugged away and then gave me its recommendations, which included spinning up PostgreSQL, creating an 'Observer' to watch my OpenClaw and Claude sessions to pull memories into the database, setting up an embedding LLM server to generate the embeddings, and then a process that runs nightly to remove duplicate memories, combine similar memories and archive old memories. If I recall almost all of these were components of OpenBrain, but I'm cautious about using other people's code and appreciate that Claude is a good tool for using ideas from other projects without actually needing to use the whole project itself.
One instance recently where I'm glad I did this was Milla Jovovich's MemPalace... since I already had a memory system in place I didn't need to use her project, but one thing I did find very intriguing was the AAAK, which she had described as a lossless compression language for AI agents. I asked Claude to evaluate all of MemPalace and see if there was anything that would be an improvement to my setup, and Claude also got excited about AAAK. Claude said that everything else we were doing was as good or better than MemPalace, but if we could add an AAAK version of each memory that would help lower the token usage (but we kept the full prose memory to help with search). We implemented it and I asked Claude to pull some random memories from the db... and it was immediately clear that there was no way AAAK was lossless because a lot of my memories had to do with system details, including IP addresses, and the AAAK didn't include any IP addresses. Of the 1800 memories that I had stored, Claude was only able to find 3 where enough meaning had been preserved with AAAK to be usable. It was easy to remove from my system - and I just checked and the project no longer refers to AAAK as lossless.
Using this method I also built a filesystem based context system that allows any LLM on my system to use the same skills, context, agents, projects, and memories (although the memory folder just has instructions on how to access the memory database). This was another project I saw from someone else and I used a lot of their ideas, but tweaked things to fit my needs.
Other tools where I am using other's projects are 'Faster-Whisper' for speech-to-text, 'Piper TTS' for text-to-speech, 'Moondream2' for image analysis and QMD Search for indexing my Obsidian Vault and putting it into the memory system.
The Chinese models are being released as open weight models, which are what people who want to run these systems locally are using. By banning them this just means that in the US only corporate models will be available to anyone.