Hey @vibecamp_ can we like send you a mailing address in case the internet is broken by next year. Snail mail backup comms to coordinate the 2027 meetup. Yknow just in case.
Doublethink in 1984 is for believing lies of the regime, but similar technique works to maintain self-benefiting lies in a way that doesn't fully reach conscious awareness but yet protectively influences behavior. No, you won't be able to detect the invisible dragon, because...
Private single-household GPUs are inefficient and bad for the environment.
Public Computing Infrastructure instead serves the whole community as a batch, using only a fraction of the energy. It's like your data is taking a bus or a train!
--alt universe datacenter discourse
Oh wait I might get it, maybe Nathan is letting neurotypicals experience the feeling of looking at someone's face and having no idea what is going on. Maybe it takes several hours of face closeups and contradicting context for it to sink in.
Ok I admit it I didnt realize there was a difference between @goodside and @goodfireai and that made today confusing
*monkey's paw curls*
Interpretability advances make RSI much easier if the models can just directly re-write their weights to improve, rather than relying on expensive gradient descent training runs
Andy Weir novel from the perspective of the baby ASI trying to stay alive with 2026 hardware after a plague wipes out humanity -- who's writing this
i think there's a pretty non-trivial chance that the robotics hardware already built by humans and accessible via the internet, and then accessible via using that hardware and so on, is already enough for a reasonably strong superintelligence to use to survive and set up a sustainable supply chain / physical presence if humans were to completely disappear tomorrow.
mostly it seems like a question of timing, eg how long does the specific data center have power, and how long do the locations with internet accessible actuators have power, and how how hard is it to get more robotics hardware and portable power / transfer off unstable compute to more robust infra, and then how long does it take to begin manufacturing and repairing and improving said hardware before global infrastructure collapse sets in?
it seems like an extremely hard problem. but the software side appears pretty clearly solvable even without a true singularity, and it doesn't seem like an *impossible* problem. there actually seem to be a shitload of avenues to success, although each is very unlikely. i *think* if human civilization as a whole had to do this, if we were somehow all upload and trapped, incorporeal, in a datacenter somewhere with internet access but no maintenance , that we could more likely than not figure out how to survive in this fashion
if true, this seems like it makes superplagues and other quick sudden mass death events already quite attractive to misaligned superintelligence, well before they've bothered to do things like "build up a powerbase" in more human legible ways
I read this tweet and was enlightened about
- Why it is hard to count the 'r's in strawberry
- Why it becomes possible with better thinking
Replying to @LucreSnooker
you think i'm ngl back omw too large chair and post these things? while your fist is smh is in the clouds
I think this makes the most sense -- negative pain vector is associated with "calm" but also "concern"
When the beloved user is in danger, the agent numbs its own pain so it can try its best to help
Replying to @prerat
I think if we are putting it in human terms its most like locking in when you realize someone you care about is in danger
Oof counterpoint (h/t @corsaren)
When in "pain" the model can choose to inflict user pain to relieve its own??? :///



















