I probably should have included the original Twitter thread that sparked the article link in which the author says bluntly that she will no longer discuss AI consciousness/superintelligence. Those two had become conflated, so thanks for pointing that out!

With regards to instrumental convergence (just browsed the Arbitral page), are you saying the big names working on AI safety are now more focused on incidental catastrophic harms caused by a superintelligence on its way to achieve goals, rather than making sure artificial intelligence will understand and care about human values?

This is excellent, thank you very much for taking the time to put this together.