Here’s a “demo” that if you give random people access to an AI, one of them might ask it to destroy humanity, just to see what would happen. Granted, I think this person had justified confidence that this particular AI would fail to destroy humanity… decrypt.co/126122/meet-... 7/16 - ThreadSky

stevebyrnes.bsky.social • 72 days ago

Here’s a “demo” that if you give random people access to an AI, one of them might ask it to destroy humanity, just to see what would happen. Granted, I think this person had justified confidence that this particular AI would fail to destroy humanity… https://decrypt.co/126122/meet-chaos-gpt-ai-tool-destroy-humanity 7/16

Comments

stevebyrnes.bsky.social•72 days ago

…but here is a “demo” that it’s possible for people to do experiments that threaten the whole world, despite a long track record of direct evidence that this exact thing is a threat to the whole world, wildly out of proportion to its benefit, and that governments may even fund them. 8/16

stevebyrnes.bsky.social•72 days ago

Here is a “demo” that, given a tradeoff between AI transparency (English-language chain-of-thought) and AI capability (inscrutable chain-of-thought but the results are better), many people will choose the latter, and pat themselves on the back for a job well done. https://arxiv.org/abs/2412.06769 9/16

stevebyrnes.bsky.social•72 days ago

Every week we get more “demos” that, if next-token prediction is insufficient to make powerful autonomous AGIs that can accomplish long-term goals via out-of-the-box strategies, then people will keep searching for other approaches that CAN do that. 10/16

stevebyrnes.bsky.social•72 days ago

Here is a “demo” that it’s possible for companies to ignore or suppress obvious future problems when they would interfere with immediate profits. 11/16

stevebyrnes.bsky.social•72 days ago

Here is a “demo” that it’s possible for there to be a global catastrophe causing millions of deaths and trillions of dollars of damage, and then immediately afterwards everyone goes back to not even taking trivial measures to prevent similar or worse catastrophes from recurring. 12/16

stevebyrnes.bsky.social•72 days ago

Here is a “demo” that the arrival of a new kind of highly competent agent with the capacity to invent technology, coordinate at scale, self-reproduce, etc., is a big friggin’ deal. https://en.wikipedia.org/wiki/Human_impact_on_the_environment 13/16

Comments

Posting Rules

Reply