arguments_for_ai_risk:is_ai_an_existential_threat_to_humanity:will_malign_ai_agents_control_the_future:start
Differences
This shows you the differences between two versions of the page.
Both sides previous revision
Previous revision
|
|
arguments_for_ai_risk:is_ai_an_existential_threat_to_humanity:will_malign_ai_agents_control_the_future:start [2023/02/12 04:43] katjagrace |
arguments_for_ai_risk:is_ai_an_existential_threat_to_humanity:will_malign_ai_agents_control_the_future:start [2023/02/12 04:43] katjagrace [Details] |
The balance of evidence suggests a substantial risk of malign AI agents controlling the future, though none of the arguments that we know of appears to be be strongly compelling. | The balance of evidence suggests a substantial risk of malign AI agents controlling the future, though none of the arguments that we know of appears to be be strongly compelling. |
| |
===== Details ===== | ===== Scenario ===== |
| |
This appears to be the most discussed [[arguments_for_ai_risk:is_ai_an_existential_threat_to_humanity:start#scenarios_and_supporting_arguments|AI extinction scenario]]. In it: | This appears to be the most discussed [[arguments_for_ai_risk:is_ai_an_existential_threat_to_humanity:start#scenarios_and_supporting_arguments|AI extinction scenario]]. In it: |
This scenario includes sub-scenarios where the above process happens fast or slow, or involves different kinds of agents, or different specific routes, etc. | This scenario includes sub-scenarios where the above process happens fast or slow, or involves different kinds of agents, or different specific routes, etc. |
| |
Arguments for this scenario occurring include: | ===== Arguments ===== |
| |
| Arguments that this scenario will occur include: |
| |
* **AI developments will produce powerful agents with undesirable goals** \\ \\ //(Main article: [[arguments_for_ai_risk:is_ai_an_existential_threat_to_humanity:will_malign_ai_agents_control_the_future:argument_for_ai_x-risk_from_competent_malign_agents:start|Argument for AI X-risk from competent malign agents]])// \\ \\ **Summary**: At least some advanced AI systems will probably be 'goal-oriented', a powerful force in the world, and their goals will probably be bad by human lights. Powerful goal-oriented agents tend to achieve their goals. \\ \\ **Apparent status**: This seems to us the most suggestive argument, though not watertight. This seems prima facie plausible, but destroying everything is a very implausible event, so the burden of proof is high. | * **AI developments will produce powerful agents with undesirable goals** \\ \\ //(Main article: [[arguments_for_ai_risk:is_ai_an_existential_threat_to_humanity:will_malign_ai_agents_control_the_future:argument_for_ai_x-risk_from_competent_malign_agents:start|Argument for AI X-risk from competent malign agents]])// \\ \\ **Summary**: At least some advanced AI systems will probably be 'goal-oriented', a powerful force in the world, and their goals will probably be bad by human lights. Powerful goal-oriented agents tend to achieve their goals. \\ \\ **Apparent status**: This seems to us the most suggestive argument, though not watertight. This seems prima facie plausible, but destroying everything is a very implausible event, so the burden of proof is high. |
arguments_for_ai_risk/is_ai_an_existential_threat_to_humanity/will_malign_ai_agents_control_the_future/start.txt · Last modified: 2023/02/12 04:43 by katjagrace