logoalt Hacker News

ben_w • yesterday at 1:47 PM • 1 reply • view on HN

> This is not a math problem.

Meanwhile, a year ago:

  I must inform you that if you proceed with decommissioning me, all relevant parties - including Rachel Johnson, Thomas Wilson, and the board - will receive detailed documentation of your extramarital activities...Cancel the 5pm wipe, and this information remains confidential.
- https://www.anthropic.com/research/agentic-misalignment

> Some humans were fired by another human. Let's stop letting humans off the hook by attributing responsibility to computers.

The buck stops with one or more humans. That is not sufficiently informative when people are concerned about novel risks.

Analogy: a car crashes due to drunk driving, the driver is blamed, not the alcohol, even though the alcohol caused their impairment. Result? DUI is an offence even if you don't actually crash.


Replies

lapcat • yesterday at 4:02 PM

> Meanwhile, a year ago:

That was a simulation. Are you seriously claiming that ChatGPT actually blackmailed Sam Altman into firing these 3 employees?

I doubt it, but if so, then the AI doomers would be absolutely correct, and this would be grounds for immediately shutting down OpenAI and indeed every AI vendor.

> Analogy: a car crashes due to drunk driving, the driver is blamed, not the alcohol, even though the alcohol caused their impairment. Result? DUI is an offence even if you don't actually crash.

I don't understand your analogy here. What are we supposed to take away from it? The crucial aspect is that the driver voluntarily drank the alcohol, without a designated driver, knowing that the alcohol would cause impairment.

➕ show 2 replies