Creating an AI policy

The gold rush has irreversibly begun, software companies are shoveling AI support into their apps, while experts in the field cannot scream loud enough about the risks. While there are infinite new opportunities, difficult to comprehend how immensely valuable, certainly there are also many dangers, which are maybe even more difficult to realize.

We as software developers and product managers have a HUGE say in what will happen and what not in cyberspace. We have way more power than we often realize. And because of that, we need to be very careful. And responsible. And we need to have principles.

Principles, by definition, should not depend on the actual opportunity. We should be prepared not to blindly follow the flow when a tempting opportunity comes if it compromises our principles. So I believe it's good to have an AI policy ready, preferably published on our website, so when I'm asked to create this or that AI integration, there is something written that I can refer to. A Ulysses pact.

So I've started to sketch an AI policy for my software development team, based on the bits that I've already understood about the risks of generative AI.

Here it is:

Our basic principle is that humans should rule over the computer and not the other way around. Therefore we do not create and do not install a system where

• an AI makes decisions about humans, without a human taking responsibility about the decision
• where an AI can uncontrolledly influence the outside world, or make uncontrolled actions on the internet

We think helping human editing work by AI is useful, however, we see the risks when the human editor only superficially verifyies the AI-generated content. Therefore, in the applications we develop, every longer (>~10 words) AI-generated content included into human-edited content will be marked with some subtle mark (color, comment). The human editor can remove this mark, thus explicitly taking responsibility for the content.

Similarly, when I code with an AI assistant, I strive not to accept longer (multi-line) AI-generated code completions at once, only line by line or word by word.

This is only my first attempt in this new genre, and I plan to further refine it as new trends are happening and my understanding of the topic broadens.

I encourage you to think about this difficult and sensitive topic. And please share your thoughts!