News for hackers. Stuff that matters.
Re:How We Rooted Copilot by blastonico on Saturday July 26, 2025 @07:22PM (#44697707)
Not really. You're referring to agents, but the model doesn't always require agents, and the public chatbot is not connected to a shell freely evaluating arbitrary commands.
Re:How We Rooted Copilot by blincoln on Sunday July 27, 2025 @08:39AM (#44700895)
> and the public chatbot is not connected to a shell freely evaluating arbitrary commands.

[ citation needed ]

Re:How We Rooted Copilot by brookst on Sunday July 27, 2025 @09:56AM (#44701348)
This is false.

Modern chatbots use tool orchestration where the LLM is given a list of tools it can use. Tools include things like searching the web and, yes, executing code. The LLM can generate arbitrary code (typically Python) and call a tool to execute it and return results. The tool takes the Python input, launches it (in a container in this example) and returns the output, which the LLM can further process.