This week I am trying to verify my lock-in with Claude and OpenAI. I will try to use pi as a harness and Kimi-K3 through EdenAI as a LLM model.
The choices are really arbitrary, mainly based on the fact that I have been reading good things about them. We will see.
My wife said she would have a difficult time to get out of ChatGPT because it remembers so much about her writing style, her preferences, her thought process.
For one of my clients they were asking whether I thought it would be a good idea to use a business account with Anthropic, so we can all pool tokens together and some manager would have a better overview of our usage. It sounds like Anthropic has been selling them advantages that mainly amount to vendor lock-in.
So now I want to try and see how tied to claude I am myself.