Untagged questions

Back to Review questions.

These 86 canonical questions don't have any tags, please add some!

How quickly could an AI go from the first indications of problems to an unrecoverable disaster?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Is it possible to code into an AI to avoid all the ways a given task could go wrong, and would it be dangerous to try that?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Could we build provably beneficial AI systems?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Why do some AI researchers not worry about alignment?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Why can't we simply stop developing AI?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Where can I learn about AI alignment?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Isn’t it immoral to control and impose our values on AI?

Edit question

Edit non-canonical answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

What is "HCH"?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

What are "selection theorems" and can they tell us anything useful about the likely shape of AGI systems?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

What does alignment failure look like?

Edit question

Edit non-canonical answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

How might an AI achieve a seemingly beneficial goal via inappropriate means?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Considering how hard it is to predict the future, why do we think we can say anything useful about AGI today?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Can humans stay in control of the world if human- or superhuman-level AI is developed?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Might an aligned superintelligence force people to "upload" themselves, so as to more efficiently use the matter of their bodies?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

What research is being done to align modern deep learning systems?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

How would we align an AGI whose learning algorithms / cognition look like human brains?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

How do I know whether I'm a good fit for work on AI safety?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Will AGI be agentic?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Why does there seem to have been an explosion of activity in AI in recent years?

Edit question

Edit non-canonical answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Why work on AI safety early?

Edit question

Edit non-canonical answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

What does Ought aim to do?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

A lot of concern appears to focus on human-level or “superintelligent” AI. Is that a realistic prospect in the foreseeable future?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Why can't we just make a "child AI" and raise it?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Might an aligned superintelligence force people to have better lives and change more quickly than they want?

Edit question

Edit answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

Is the UN concerned about existential risk from AI?

Edit question

Write answer

Reader UI

Mark as:

Not canonical

Out of scope

Duplicate

Review as:

Meh

Unreviewed

Approved

Good

Excellent

Tags: None (add tags)

See more...