How does he know that the response isn't just hallucinations?

I'm telling it because I work there and I don't recognize any of those processes.

In fact I found one script named keepAliveJupyterSvc.sh in a public repo: https://github.com/shivamkm07/code-interpreter/blob/load-tes...

▲

eddythompson80 3 days ago | parent | next [-]

That repo, and its contributors are MS/Azure employees working on the service for running python code in a container. I don't know why it's under a personal account. Though it says it's a fork from an Office repo that I can't find.

▲

what 3 days ago | parent [-]

How do you figure? I don’t see anything that suggest they work for ms/azure?

	▲	eddythompson80 3 days ago \| parent [-]
		The repo’s owner Employer listed on their profile? Also you can add .patch to any GitHub commit url and get a git patch file https://github.com/shivamkm07/code-interpreter/commit/5e282c...

▲

jon_adler 3 days ago | parent | prev | next [-]

It may not be a hallucination. Perhaps the Copilot code was generated from the GitHub training set?

▲

blastonico 4 days ago | parent | prev [-]

Oh boy, this really seems to be hallucination.

Guys, chatbots are mostly token generators, they don't run programs e give you responses...it's not a simple shell program, it computes things in GPU and return tokens, in which are translated back to English.

▲

MattGaiser 3 days ago | parent [-]

This is very out of date. They now often trigger tooling and return the outputs of the tooling.

▲

blastonico 3 days ago | parent [-]

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.

	▲	brookst 3 days ago \| parent \| next [-]
		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.
	▲	blincoln 3 days ago \| parent \| prev [-]
		> and the public chatbot is not connected to a shell freely evaluating arbitrary commands. [ citation needed ]