About 90% of my coding is on Qwen 3.6 27b and Open Code with some custom skills and Semble. It is NOT as smart as CC or Codex but its enough to get most of my work done. I didn't set out to replace CC and Codex (I have an RTX 6000 so the TPS is faster than I care about, but the RTX 6000 was originally for other work). I only tried this just to see how close you could get to a frontier model for coding as an experiment, but it was good enough that I stuck with it. I still fall back to Codex for really complicated stuff and to polish UI's as that seems to be the weakest element to working in Qwen.This isn't a recommendation because I don't think most people have an RTX 6000 laying around and the cost would be many years of MAX CC or Codex subscriptions, but at least this seems possible. Maybe in a few more years it will even be practical.
Other Notes: I have had to set the compact target to 75% on a 256k context window as once the conversation length goes about 100k I start seeing a drop in the quality and speed. This becomes very problematic after about 150k. I tried Qwen 3.5 122b too but it actually seems much worse at coding than 3.6 27b even though its much larger. Maybe because I am using a 4bit quant or maybe I just don't have it configured correctly? I know 3.6 is newer but I didn't expect it to out perform a model that is much larger from the prior generation. Gemma 4 31b is a good model for other tasks but at least my personal experience is that Qwen outperforms in coding. Nemotron Super 120b is great at a lot of stuff but it also seems to be not as good at coding as Qwen. This was very surprising to me.
In the US -- once our nation finishes attacking our own education system -- this is definitely something a group of academic institutions could get together and accomplish. I assume the same is true in other countries. Companies like Nvidia and AMD might even support that effort, as they make money on the hardware and would probably be more than happy for there to be more reasons to use it. There may have not been a compelling enough motivation to achieve this before, but "models" didn't have this level of strategic relevance until relatively recently. Nvidia has been fairly good about releasing open weight models in the last few months.
A mod that fixed a bug that prevented certain buffs from working when mounted for the Magus class / Arcane Rider archetype in Pathfinder Wrath of the Righteous. It also managed to fix the problem with Shelters not providing protection from corruption when resting in outposts in that same mod. I've used other models to expand the mod to an entire mini-expansion with new Archetypes and abilities since then.
I had a locally hosted model write its own semantic search system that indexed 250,000 documentation and code files and then write a fully functioning mod for one of the games I play based on that documentation that I couldn't get to work after 2 weeks of my own effort, all in under 4 hours (and that included a 25 minute long indexing process). This freaked me out enough that I then had it write a CLI based activity and TODO tracker and then integrate that tool into its coding process to track all of its activities in about another 2 hours. I am still emotionally recovering from this day. I have since replaced the semantic search system with an open source option (though I used it for a few months) but I still use the activity tracker for both coding projects and myself.
I am a 'fan' of Open Web UI, but the document editing mode is a compelling feature that Open Web UI does not have. I'll probably wait a while before trying Odysseus... let the inevitable security problems work themselves out.
In a related story... I got led on by Eliza. I tried to have a productive conversation and she just kept asking me redundant questions. It's obvious that she was trying to extend the conversation for nefarious reasons that I can only guess at. It's true I approached her and started the conversation, but I hardly think that makes me blamable for what happened here.
I have exposure to AI initiatives at several companies including a few F500's. I have seen teams dump huge logs into frontier models that took hours to get so-so results that we were able to replace with a few lines of python code at 1000 times the speed and 100% accuracy. When asked why they were doing this they literally said "because we don't understand the subject matter so we were depending on the AI". I saw one team file a complaint with a vendor about a frontier backed coding harness and it's inability to consistently format headers because they were using it as a reporting engine. When I recommended they just use the coding tool to write code to generate reports you would have thought I had just cured cancer from their response. I frequently see people complain about the fact that AI is going to take their jobs and then see them gripe about the fact that AI is 'worthless' because it can't do more of their job than it already does. It's easy to see the difference between the people seeing 10x productivity gains from leveraging AI and those who aren't and it's not the AI.
"It's one of the few places where otherwise smart people make confident statements that they don't even realize they can't support until they're asked to try."
It's 'one' of the few places? That behaviorism seems to be define almost all modern discourse from politics to health care including about 95% of Hacker News posts as far as I can tell...
So about a year ago I wrote my own attempt at something like this using vector indexing and BM25 (the latest version uses CocoIndex, I had a custom coded solution using ChromaDB before). I wrote a comprehensive enough test set that showed performance increases on the quality of search results and reduction in token usage versus grep and rg. I haven't had time to really polish it but it worked well enough, particularly for one project where I have around 250k documentation files and docs out number code files 1000 to 1 (about 50% reduction in tokens and 30% increase in successful searches). Yesterday for grins I tried this project and was fairly disappointed to see it blow away my kludged solution particularly given that it doesn't have a lengthy indexing process. I haven't tested it on the 250k doc project yet, but in another project that I have a test suite for semantic search on it outperformed my solution by about 20% even on documentation in terms of successful search results (which I didn't expect given that it seems to only be tuned for code). I haven't gone through the code to see what its doing differently than what I tried, but what ever its doing it seems to have potential.
A more insidious related pathology- marital induced projected LLMorphism... where your wife constantly accuses you of having the personality of a large language model.
Great work! Though I see some people criticizing the usefulness of this. Are they being sarcastic are just really not understanding what is being discussed here? I can't tell. Maybe as an interesting follow up you could train the transformer on something with a more limited vocabulary. Spoken language is complex but a transformer can work on less complex domains like music or PET-BASIC code.
The general take here seems to be "everything eventually passes". That isn't always true. I wonder how many people have a primary computing device that they don't even have full control over now (Apple phones, tablets...). Years ago the concept of spending over $1k on a computer that I didn't even have the right to install my own software on was considered ridiculous by many people (myself included). Now many people primarily consume content on a device controlled almost entirely by the company they bought it from. If the economics lead to a situation where its more profitable to sell you compute time than sell you computers then businesses will chose to not sell you computers. I have no idea if that is what ends up happening.
This looks like one of the rare instances where a company tried to balance their commercial interests with the interest of the fans of their products. I don't see why people would be complaining?
Does it seem to anyone else that author's have created a definition for 'vibe coding' that is specifically designed to justify their paper? Also that their premise is based on the assumption that developers will be irresponsible about the use of these tools ("often without users directly reading documentation, reporting bugs, or otherwise engaging with maintainers") so that it would actually be people killing open source not 'Vibe Coding'? Just a guess on my part, but once developers learn to use these tools and we get over the newness I think this will be great for open source. With these tools open source projects can compete with an army of corporate developers while alleviating some of the pressure on overworked under-rewarded maintainers.