At this point I think it’s more important to have a solid workflow and understanding of how [insert your favorite model here] works and its capabilities, than chasing the next shinny release jumping back and forth between companies. I just finished my first large project with Codex and it is hard for me to believe Claude can be much better. It may be a bit better or worse, but again, they are all so good now that the user is the one driving the difference.
There is currently quite strong incentive to establish vendor lock-in for Anthropic and OpenAI. I see the ability to jump between companies quite important, especially for larger users. Right now it should not be hard but it can be much harder in the future.
