Re:New models and developer products announced at OpenAI DevDay
by skybrian on Monday November 06, 2023 @04:47PM
(#38169482)
Yes. Hopefully, sandboxing limits the damage somewhat, but it doesn't help if you put any private docs in the sandbox.
Also, the limitations of the Code Assistant tool's server-side Python sandbox aren't described in their API docs. In particular, when does the sandbox get killed? Anyone know? If they're similar to the Code Assistant tool in ChatGPT, then it kills your sandbox within an hour or so (if you go to lunch) which is a crappy user experience.
Running the sandbox on the user's machine seems like a better approach. There's no reason to kill the sandbox if it's not using any server-side resources. Maybe the function-calling API would be useful for that, somehow?
The most immediately useful thing is the price cut, though.
Also, the limitations of the Code Assistant tool's server-side Python sandbox aren't described in their API docs. In particular, when does the sandbox get killed? Anyone know? If they're similar to the Code Assistant tool in ChatGPT, then it kills your sandbox within an hour or so (if you go to lunch) which is a crappy user experience.
Running the sandbox on the user's machine seems like a better approach. There's no reason to kill the sandbox if it's not using any server-side resources. Maybe the function-calling API would be useful for that, somehow?
The most immediately useful thing is the price cut, though.