AI for president

[pocaracas]

Inspired by this reply from Thump

I think all of those "impredictable" /* Leviathan-like politicians around the world should be replaced by some sort of AI. Call me futuristic but I don’t see any other solution

That is a ferociously bad idea. It really deserves its own thread, so I won't clutter this thread up with further debate on it.

I was wondering what are the pros and cons of such an AI replacing the political class.

ChatGPT gave me these pros and cons:

Replacing the political class with AI is a huge idea — and while it's kind of sci-fi sounding, it's also increasingly part of real-world debates. Let's break it down into pros and cons, assuming a hypothetical future where AI is advanced enough to manage complex governance tasks.
✅ Pros of AI Replacing the Political Class

•  No Corruption or Personal Interests
         AI doesn't lobby for votes, take bribes, or act out of self-interest.
         It could make decisions based on data and the public good, not political gain.
  
•    Faster, Data-Driven Decision Making
         AI can analyze massive datasets instantly to make informed choices.
         It could respond to crises (like pandemics or economic shifts) with speed and precision.
  
•  Consistency & Predictability
         Unlike humans, AI wouldn’t flip-flop based on polling or public pressure.
         Long-term policy planning becomes more stable and coherent.
  
•    No Ego or Tribalism
         No party lines, no populism, no campaigning.
         The focus could be on solutions rather than ideology or power struggles.
  
•  Accessibility & Transparency (potentially)
         If designed properly, AI decisions could be made fully transparent and explainable.
         People could see how and why decisions are made, unlike closed-door negotiations.
  

❌ Cons of AI Replacing the Political Class

• Democratic Deficit
         People would lose the ability to elect their leaders.
         Who controls the AI? Who decides what values it should follow?
  
• Bias & Programming Issues
         AI reflects the biases of its creators and the data it's trained on.
         It could accidentally perpetuate inequality or injustice.
  
•    Lack of Empathy
         Governance isn’t just logic — it’s also emotional intelligence and human connection.
         AI might struggle with nuanced moral issues or human suffering.
  
•    Accountability Problems
         If the AI makes a bad decision, who is responsible?
         You can’t vote out an algorithm.
  
•    Security & Manipulation Risks
         What happens if the system is hacked, or manipulated by insiders?
         A centralized AI system could be a single point of failure.
  
•    Cultural & Ethical Blind Spots
         AI might struggle to understand local cultures, traditions, or evolving social norms.
         It might impose technocratic solutions that don't resonate with communities.

I see many desirable pros, while the cons can be sorted with having a sort of human comitee overseeing the AI in a kind of hybrid solution.
Of course, any AI at this position needs to be capable of continuously learning from the world. It can then easily become biased from that source of information, so it is important to make it so that it gathers data from international sources, taking into account their own biases... kinda like the app that youtubers keep advertising.

[Alan V]

Since people like to scapegoat their leaders for problems which are beyond their leaders' control, I'm not sure AI would function so well in that role.

AI would likely say, "Hey, I can't control that," instead of promising what is impossible to begin with.

[Fake Messiah]

That's what Elon Musk is trying to do: replace government workers with AI which ultimately leads to the president. And who controls AI? The tech bros.

But maybe there shouldn't be a president at all. Certainly all these congressmen and senators could do his job because it's just too much power for one person.

[Mister Agenda]

As long as it was born in the USA and at least 35 years old, I do not object to an AI running for president.

[Fireball]

Probably wouldn't be any worse than the crazy meat bag holding the office at present.

[Thumpalumpacus]

The negatives outweigh the positives. And let's face it, AI is notoriously wrong about basic facts on many occasions.

[BrianSoddingBoru4]

Sarah Connor would like a word…

Boru

[AFTT47]

Way too early to consider anything like that. AI is in its infancy and we don't even know what we don't know. Revisit this in 10 years.

[arewethereyet]

At this point, I would take a rotting turnip over what we currently have.

[Angrboda]

I'm reminded of questions about how we should vet AI. People would be alarmed to put life & death decisions in the hands of AI, yet we're remarkably blase about giving 20 year-olds rifles and pointing them toward the front.