Is not working with gpt5.x models (Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.) which is hardcoded. I dont know why this is on the front page. My review-with-codex skill is working just fine, consuming my usage and not API tokens.
I'm sorry — we didn't expect to receive so much attention from the developer community so soon after open-sourcing the project. Some parts of the codebase are not yet fully polished. We are currently refactoring the LLM module and will address this as soon as possible. Once again, I sincerely apologize for the inconvenience.
"That is a classic "efficiency vs. logic" dilemma.
If you’re looking for a strictly practical answer: Drive. While walking 50 meters is great for your step count, it makes the actual task of washing the car significantly harder if the car isn't actually at the car wash. Unless you’ve mastered the art of long-distance pressure washing, the vehicle usually needs to be present for the scrubbing to commence."
I think it's also the case that AI code can be insanely bad despite being well-formatted and sometimes very good when it comes to specific functionality. But you have to keep watching out for code that doesn't do anything or replicates existing functionality or devolves into complete loose ends. Actual human code is much more pleasant by comparison.
There's enough of a market for them to exist these days. The issue is that companies want to treat VR headsets as if they're in the same category as phones or even tablets, when really, they're closer to the same category as, say, racing rigs or other highly hobby-specific products.
