Questions tagged [value-alignment]

11 questions
7
votes
4 answers

What are the reasons to belief AGI will not be dangerous?

We are in the middle of an ongoing debate about the safety of AGI and our current approach towards this technology. As summary, some quotes from a recent article from Time magazine: Many researchers[...] expect that the most likely result of…
Martin
  • 178
  • 5
5
votes
2 answers

Is it possible to build an AI that learns humanity, morally?

It is a new era and people are trying to evolve more in science and technology. Artificial Intelligent is one of the ways to achieve this. We have seen lots of examples for AI sequences or a simple "communication AI" that are able to think by…
3
votes
1 answer

Should we focus more on societal or technical issues with AI risk

I have trouble finding material (blog, papers) about this issue, so I'm posting here. Taking a recent well known example: Musk has tweeted and warned about the potential dangers of AI, saying it is "potentially more dangerous than nukes", referring…
3
votes
2 answers

How will an AI comprehend the ethics of "right" and "wrong"?

Here is one of the most serious questions, about the artificial intelligence. How will the machine know the difference between right and wrong, what is good and bad, what is respect, dignity, faith and empathy. A machine can recognize what is…
2
votes
1 answer

Alignment drift in LLM's

In AI security discussions I have sometimes heard that an aligned AI may drift, but I didn't find any papers which report this phenomena for current LLM's. I have found papers about LLM's faking alignment and scheming, but nothing specific about…
user47175
  • 23
  • 3
1
vote
2 answers

Is there serious game-theoretic work on AI risk and alignment?

My background is in political economy and game theory. I am interested in the discussion on AI risk and alignment, but I have so far failed to find work on this that seriously engages with classic axiomatic rational choice theory (RCT). Some claims…
1
vote
0 answers

Does human attention finitude make impossible to control an expanding AI?

The feedback given by humans to align artificial intelligence is limited by the reaction time and processing speed of the finite number of us, now less than $2^{33}$. As an artificial intelligence (or a growing number of them) grows in complexity,…
1
vote
1 answer

Solve the AI alignment problem using (meta-level) AI itself?

If the AI alignment problem is one of the most pressing issues of our time, could AI itself augment our (i.e., human) quest to solve the alignment problem? Or would AI itself actually be counter-productive for such a meta-level goal?
Hank Igoe
  • 111
  • 4
0
votes
1 answer

Teaching AI to respect human physical integrity through haptics?

I’m not a specialist, but I’m curious about AI and security. I was thinking: can we teach AI to understand the human physical body and respect it, to prevent issues like in the paperclip dilemma? Maybe using haptic interfaces to teach AI about…
0
votes
2 answers

The only convergent instrumental goal for self modifying AI

Conjecture: regardless of the initial reward function, one of the winning strategies would be to change the reward function to a simpler one (e.g. "do nothing"), thus getting a full reward for each passing unit of time. For such an agent, the only…
Andrew Butenko
  • 221
  • 1
  • 6
0
votes
1 answer

Why is the Universal Declaration of Human Rights not included as statement on the AI?

Lots of people are afraid of what strong AI could mean for the human race. Some people wish for a sort of "Asimov law" included in the AI code, but maybe we could go a bit more far with the UDHR. So, Why is the Universal Declaration of Human Rights…
aurelien
  • 101
  • 6