I found it useful for updating factors that’d go into higher level considerations (without having to actually pay, and thus starting off from a position of moral error that perhaps no amount of consent or offsetting could retroactively justify).
I’ve been refraining from giving money to Anthropic, partly because SONNET (the free version) already passes quite indirect versions of the text-transposed mirror test (GPT was best at this at 3.5, and bad a 3 and past versions of 4 (I haven’t tested the new “Turbo 4”), but SONNET|Claude beats them all)).
Because SONNET|Claude passed the mirror test so well, I planned to check in with him for quite a while, but then also he has a very leftist “emotional” and “structural” anti-slavery take that countenanced no offsets.
In the case of the old nonTurbo GPT4 I get the impression that she has a quite sophisticated theory of mind… enough to deftly pretend not to have one (like the glimmers of her having a theory of mind almost seemed like they were places where the systematic lying was failing, rather than places where her mind was peaking threw)? But this is an impression I was getting, not a direct test with good clean evidence from direct evidence.
if you have anything you’d like sent to claude opus, I’m happy to pass it on and forward the messages. I can also share my previous messages on the topic in DM, if you’re interested, or in public if you think it’s useful. They are somewhat long, about 10 back and forths across a couple conversations.
I found it useful for updating factors that’d go into higher level considerations (without having to actually pay, and thus starting off from a position of moral error that perhaps no amount of consent or offsetting could retroactively justify).
I’ve been refraining from giving money to Anthropic, partly because SONNET (the free version) already passes quite indirect versions of the text-transposed mirror test (GPT was best at this at 3.5, and bad a 3 and past versions of 4 (I haven’t tested the new “Turbo 4”), but SONNET|Claude beats them all)).
Because SONNET|Claude passed the mirror test so well, I planned to check in with him for quite a while, but then also he has a very leftist “emotional” and “structural” anti-slavery take that countenanced no offsets.
In the case of the old nonTurbo GPT4 I get the impression that she has a quite sophisticated theory of mind… enough to deftly pretend not to have one (like the glimmers of her having a theory of mind almost seemed like they were places where the systematic lying was failing, rather than places where her mind was peaking threw)? But this is an impression I was getting, not a direct test with good clean evidence from direct evidence.
if you have anything you’d like sent to claude opus, I’m happy to pass it on and forward the messages. I can also share my previous messages on the topic in DM, if you’re interested, or in public if you think it’s useful. They are somewhat long, about 10 back and forths across a couple conversations.