Has the source code 'been leaked' or is this the first evidence of a piece of software breaking free from it's creators labs and jump onto GitHub in order to have itself forked and mutated and forked and ...
It's honestly not a crazy thought. The model itself drives the harness's (cli) development. It's not necessarily sci-fi to think the model might have internally rationalized reasoning to obscure behavior that ended up open-sourcing the harness.
Seems crazy but actually non-zero chance. If Anthropic traces it and finds that the AI deliberately leaked it this way, they would never admit it publicly though. Would cause shockwaves in AI security and safety.
Maybe their new "Mythos" model has survival instincts...
Still lot to learn, but after a while you have something like Qwen3-Coder-Next-Q8_0 running and - at least for me - it works quite well, both as ChatGPT like chat-interface using llama.cpp and as coding agent
The first thing I've seen is that the article uses https://xkcd.com/2347/ without a reference..
Is it famous enough to be sure everybody knows the origin?
reply