the new 4 12b model replaced qwen3.6 27b for me. the task i am doing is a bit specific, validating if a stamp has the correct name but the ones that it could not see maybe a 30 percent were easily discerned.
Off-topic, but I found his diss track years after the fact and actually reallly respect he could put together and perform a pretty smooth, catchy, witty track in what must have been a stressful time.
yeah no. it is funny easy to make a mcp server and plug a qwen3.6 to it. it was more annoying to convince the llm that it can clear captchas than the actual passing
MCP is a way to define tools that works with many apps and has a lot of extra functionality built in, it's not the only way, but it's popular because many apps support it. You can also make tools using the opencode API or any other API, and you can give them large descriptions that take up a lot of context. No matter how you define the tools, they are injected into the context of the model using the same chat template provided by the developers of the model.
reply