Just a brief note to mention that when I was fighting Codex CLI earlier this week to call the OpenAI Whisper API , what was really going on was that Codex CLI was sandboxed. ChatGPT helped me modify the script I was creating so that the script itself punched through the sandbox by clearing the proxies that had been setup to keep Codex CLI in the secondbox. It's interesting that ChatGPT didn't just tell me to add the --yolo argument to my codex cli command line. I wonder if that's part of its guardrails, or if ChatGPT doesn't know about the arguments to Codex CLI yet through training. I saw similar things happen when ChatKit was announced. ChatGPT wasn't quite sure what it was on the day of the announcement. The good new is that I'm now calling APIs without any shenanigans because I learned to simply add '--yolo' the following day. That argument comes with its own set of risks, but I'm ok with those for the moment.