On human-computer interfaces:
Working memory, knowledge reservoirs and raw calculation power seem like the easiest pieces, while fundamentally making people better at critical thinking, philosophy or speeding up actual comprehension would be much for difficult.
The difference being upgrading the core vs plug-ins.
Curated reservoirs of practical and theoretical information, well indexed, would be very useful to super geniuses.
On human-human:
You don’t actually need to hook them up physically. Having multiple people working on different parts of a problem lets them all bounce ideas off each other.
Overall:
The goal should be to create a number of these people, then let them plan out the next round if their intelligence doesn’t do it.
If humanity can make 100 7+SD humans hooked up with large amounts of computing power, curated knowledge + tons of raw data, and massive working memories, they’ll be able to figure out any further steps much better than we can.
Curated reservoirs of practical and theoretical information, well indexed, would be very useful to super geniuses.
You don’t actually need to hook them up physically. Having multiple people working on different parts of a problem lets them all bounce ideas off each other.
But both of these things are basically available currently, so apparently our current level isn’t enough. LLMs + google (i.e. what Perplexity is trying to be) are already a pretty good index; what would a BCI add?
Overall: The goal should be to create a number of these people, then let them plan out the next round if their intelligence doesn’t do it.
I’m not sure how well curated and indexed most information is.
Working memory allows for looking at the whole picture at once better with the full might of human intelligence (which is better at many things than LLMs), while removing frictions that come from delays and effort expended in search for data and making calculations.
Of course we have smart people together now, but getting multiple 7+SD people together would have many further benefits beyond having them work solo.
We probably have at least a generation (we’re probably going to slow down before we hit SAGI due to the data wall, limited production of new compute, and regulation).
The focus should be on moving quickly to get a group ecliping current human capabilities ASAP, not on going much further
I’m not sure how well curated and indexed most information is.
Working memory allows for looking at the whole picture at once better with the full might of human intelligence (which is better at many things than LLMs), while removing frictions that come from delays and effort expended in search for data and making calculations.
How specifically would you use BCIs to improve this situation?
I can only describe the Product, not the tech. The idea would be to plug in a bigger working memory in the area of the brain currently holding working memory. This is the piece I think matters most
On reflection something like wolfram alpha should be enough for calculations, and a well indexed reservoir of knowledge with an LLM pulling up relevant links with summaries should be good enough for the rest
On human-computer interfaces: Working memory, knowledge reservoirs and raw calculation power seem like the easiest pieces, while fundamentally making people better at critical thinking, philosophy or speeding up actual comprehension would be much for difficult.
The difference being upgrading the core vs plug-ins.
Curated reservoirs of practical and theoretical information, well indexed, would be very useful to super geniuses.
On human-human: You don’t actually need to hook them up physically. Having multiple people working on different parts of a problem lets them all bounce ideas off each other.
Overall: The goal should be to create a number of these people, then let them plan out the next round if their intelligence doesn’t do it.
If humanity can make 100 7+SD humans hooked up with large amounts of computing power, curated knowledge + tons of raw data, and massive working memories, they’ll be able to figure out any further steps much better than we can.
But both of these things are basically available currently, so apparently our current level isn’t enough. LLMs + google (i.e. what Perplexity is trying to be) are already a pretty good index; what would a BCI add?
I commented on a similar topic here: https://www.lesswrong.com/posts/jTiSWHKAtnyA723LE/overview-of-strong-human-intelligence-amplification-methods?commentId=uZg9s2FfP7E7TMTcD
I’m not sure how well curated and indexed most information is.
Working memory allows for looking at the whole picture at once better with the full might of human intelligence (which is better at many things than LLMs), while removing frictions that come from delays and effort expended in search for data and making calculations.
Of course we have smart people together now, but getting multiple 7+SD people together would have many further benefits beyond having them work solo.
We probably have at least a generation (we’re probably going to slow down before we hit SAGI due to the data wall, limited production of new compute, and regulation).
The focus should be on moving quickly to get a group ecliping current human capabilities ASAP, not on going much further
How specifically would you use BCIs to improve this situation?
I can only describe the Product, not the tech. The idea would be to plug in a bigger working memory in the area of the brain currently holding working memory. This is the piece I think matters most
On reflection something like wolfram alpha should be enough for calculations, and a well indexed reservoir of knowledge with an LLM pulling up relevant links with summaries should be good enough for the rest