Will prioritizing corrigible AI produce safe results? | Manifold

Will prioritizing corrigible AI produce safe results?

4

Ṁ1kṀ170

2050

45%

chance

1H

6H

1D

1W

1M

ALL

This market is conditional on the market "Will the company that produces the first AGI have prioritized Corrigibility?" (https://manifold.markets/PeterMcCluskey/will-the-company-that-produces-the). This market will resolve as N/A if that market resolves as NO or N/A.

If that market resolves as YES, this market will resolve one year later, to the same result that the market "Will AGI create a consensus among experts on how to safely increase AI capabilities?" (https://manifold.markets/PeterMcCluskey/will-agi-create-a-consensus-among-e) is resolved as.

I will not trade in this market.

Technical AI Timelines

Get

1,000

to start trading!

People are also trading

By 2027 will there be a well-accepted training procedure(s) for making AI honest?

Will AI continue to improve?

AI honesty #2: by 2027 will we have a reasonable outer alignment procedure for training honest AI?

Will ARC's Heuristic Arguments research substantially advance AI alignment before 2027?

Will AGI create a consensus among experts on how to safely increase AI capabilities?

Will AI be considered safe in 2030? (resolves to poll)

Conditional on AI alignment being solved, will governments or other entities be capable of enforcing use of aligned AIs?

Will AI be capable of fast self improvement before physical AI robots are massively used for improving AI capabilities?

Before 2028, will there be a major self-improving AI policy*?

Will AGI be a problem before non-G AI?

Related questions

By 2027 will there be a well-accepted training procedure(s) for making AI honest?

Will AI continue to improve?

AI honesty #2: by 2027 will we have a reasonable outer alignment procedure for training honest AI?

Will ARC's Heuristic Arguments research substantially advance AI alignment before 2027?

Will AGI create a consensus among experts on how to safely increase AI capabilities?

Will AI be considered safe in 2030? (resolves to poll)

Conditional on AI alignment being solved, will governments or other entities be capable of enforcing use of aligned AIs?

Will AI be capable of fast self improvement before physical AI robots are massively used for improving AI capabilities?

Before 2028, will there be a major self-improving AI policy*?

Will AGI be a problem before non-G AI?