Ask your AI what’s wrong with your ideas, not what’s right, and then only trust the criticism to be valid if there are actual defeaters you can’t show you’ve beaten in the general case. Don’t trust an AI to be thorough, important defeaters will be missing. Natural language ideas can be good glosses of necessary components without telling us enough about how to pin down the necessary math.
Ask your AI what’s wrong with your ideas, not what’s right, and then only trust the criticism to be valid if there are actual defeaters you can’t show you’ve beaten in the general case. Don’t trust an AI to be thorough, important defeaters will be missing. Natural language ideas can be good glosses of necessary components without telling us enough about how to pin down the necessary math.