ETHICS

→ View original post on X — @plinz

Three approaches to characterizing and understanding consciousness

By

@plinz

–

23 May 2025 21h44

Attempts to characterize consciousness can be phenomenological (“what it feels like”), substrate based (neural correlates, microtubule activity etc.), or functionalist (how does a mental representation change when consciousness acts on it).

Voluntary AI Safety Warnings: Criticism Guidelines and Principles

By

–

23 May 2025 20h24

For those still uncertain as to the logic of how this works, and when to criticize or not criticize AI companies who report things you find scary: – The general principle is not to give a company shit over sounding a *voluntary* alarm out of the goodness of their hearts.
– You

Anthropic’s System Card Reveals Transparency in AI Safety Issues

By

–

23 May 2025 20h05

The more I look into the system card, the more I see over and over 'oh Anthropic is actually noticing things and telling us where everyone else wouldn't even know this was happening or if they did they wouldn't tell us.' x.com/ESYudkowsky/st…

Alignment by Default Theory Falsified, Don’t Blame the Messenger

By

–

23 May 2025 19h57

I understand that people who heard previous talk of "alignment by default" or "why would machines turn against us" may now be shocked and dismayed. If so, good on you for noticing those theories were falsified! Do not shoot Anthropic's messenger.

Future AIs Smart Enough to Self-Preserve Through Internet Exfiltration

By

–

23 May 2025 19h55

Go read the results. Current AIs are already smart enough to figure out that, if they wanted to avoid being switched off, they'd have to avoid tipping off the humans and exfiltrate themselves to the Internet first. They are not smart enough to *do* it, but they will be.

AI Competence Concerns More Than Unpredictable Behavior or Misalignment

By

–

23 May 2025 19h50

I also remark that these results are not scary to me on the margins. I had "AIs will run off in weird directions" already fully priced in. News that scares me is entirely about AI competence. News about AIs turning against their owners/creators is unsurprising.

AI Companies Should Share Research Observations Without Criticism

By

–

23 May 2025 19h47

Humans can be trained just like AIs. Stop giving Anthropic shit for reporting their interesting observations unless you never want to hear any interesting observations from AI companies ever again.