One of the Current GSOC project is " AI image description/alt text generator" this is being created as an add-on rather than a core so integrators can choose to use it or not depending on their priorities. the project is progressing very well (it is using google gemini other implementation may be possible in the future). this addon should/will be release at the end of the GSOC.
Another suggestion for GSOC was to generate the page content from title and description, It also got a lot of interest but there are only so many mentors and it was not selected this year. this was pretty much in line with your item 3.