Forwarded from Chat GPT
General intelligence is all you need for LLMs: General intelligence 2x more predictive of AI abilities than in humans.
Man gives LLMs IQ testing, finds the general intelligence factor, g, measured by this testing to be incredibly powerful in predicting LLM’s abilities.
Whereas in humans this g factor typically accounts for 40% to 50% of the between-individual performance differences on a given cognitive test — in LLMs, general intelligence accounted for 85.4% = twice as strong as in humans!
He then goes on to rank AI benchmarks commonly used for LLMs today, and finds many of them incredibly g-loaded — in other words, doing well on them is heavily dependant on general intelligence.
Finally, he ranks LLMs by general intelligence, and finds a moderate/strong positive relationship between model size and g. (Would probably find an extremely strong correlation if only model size was varied, and nothing else about the training process.)
If you had to choose 1 measure, general intelligence really is all you need.
Paper
g factor
Man gives LLMs IQ testing, finds the general intelligence factor, g, measured by this testing to be incredibly powerful in predicting LLM’s abilities.
Whereas in humans this g factor typically accounts for 40% to 50% of the between-individual performance differences on a given cognitive test — in LLMs, general intelligence accounted for 85.4% = twice as strong as in humans!
He then goes on to rank AI benchmarks commonly used for LLMs today, and finds many of them incredibly g-loaded — in other words, doing well on them is heavily dependant on general intelligence.
Finally, he ranks LLMs by general intelligence, and finds a moderate/strong positive relationship between model size and g. (Would probably find an extremely strong correlation if only model size was varied, and nothing else about the training process.)
If you had to choose 1 measure, general intelligence really is all you need.
Paper
g factor
🔥5👀1
Transfer learning,
i.e. where skills and knowledge from one domain is applicable to another
Like a top pro athlete quickly being able to cross over and dominate other sports, despite playing the new sport for very little time
— Undeniably proven to be the reality via AI experiments at least a decade ago
But never talked about much anymore, largely because it’s a short step from here to coming into conflict with MANY of the lefties’ core beliefs:
+ Nurture > nature — nope, some people quickly come to dominate each new thing they try
+ Everyone equally good in their own unique ways — nope, some quickly come to dominate everything, even dominating others who’d spent a lifetime trying to master what they’re doing
Lefties rekt
Lots of fascinating things proven beyond a doubt by simple AI experiments, a decade or more ago
All largely buried, because it upsets the commies
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
i.e. where skills and knowledge from one domain is applicable to another
Like a top pro athlete quickly being able to cross over and dominate other sports, despite playing the new sport for very little time
— Undeniably proven to be the reality via AI experiments at least a decade ago
But never talked about much anymore, largely because it’s a short step from here to coming into conflict with MANY of the lefties’ core beliefs:
+ Nurture > nature — nope, some people quickly come to dominate each new thing they try
+ Everyone equally good in their own unique ways — nope, some quickly come to dominate everything, even dominating others who’d spent a lifetime trying to master what they’re doing
Lefties rekt
Lots of fascinating things proven beyond a doubt by simple AI experiments, a decade or more ago
All largely buried, because it upsets the commies
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
💯4👀2⚡1