Yes, just ask your agent to formally verify your code, it will probably suggest Verus (for Rust), or SPARK (for Ada), or other similar tools. There are many. No special harness needed, the western frontier models are very good at this stuff.
This is a great concept, but I want to see more recent videos. Not videos uploaded 6-9 months ago. It would be great to be able to filter for videos uploaded in the last month.
Open source doesn't mean "anyone can use the source code commercially". Open weights similarly doesn't mean the weights can be used for anything. It just means the weights are open for anyone to download and inspect.
> Open source doesn't mean "anyone can use the source code commercially".
Yes it does. It might have requirements that you release the code for any changes you make to it or link with it. But no OSI (or FSF) approved license prohibits you from using it commercially.
I'm a little confused by your distinction between vendor and lab. AI2 (Allen Institute for AI) is a western lab and they did release a fully open source model, with open weights, data, and training code (Olmo3).
Take ModernBert, add a fully connected layer with 255 outputs, take a bunch of classification datasets from Huggingface, write the code to have the datasets fit the jev format on these 255 outputs, do supervised fine tuning on the datasets with that format. then use a confidence loss of some kind
Asking as a curious bystander: would that be sufficient?
I'm not familiar with ModernBert (my understanding stops around the original Bert), but it feels like this is asking it to do lots of heavy lifting. Can it do that much?
reply