@[email protected] to [email protected]English • 16 days agoAnthropic has developed an AI 'brain scanner' to understand how LLMs work and it turns out the reason why chatbots are terrible at simple math and hallucinate is weirder than you thoughtwww.pcgamer.comexternal-linkmessage-square169fedilinkarrow-up1408
arrow-up1408external-linkAnthropic has developed an AI 'brain scanner' to understand how LLMs work and it turns out the reason why chatbots are terrible at simple math and hallucinate is weirder than you thoughtwww.pcgamer.com@[email protected] to [email protected]English • 16 days agomessage-square169fedilink
minus-square@[email protected]linkfedilinkEnglish5•15 days agoBut you wouldn’t multiply, say, 74*14 to get the answer.
minus-square@[email protected]linkfedilinkEnglish3•edit-215 days agoI might. Then I can subtract 74 to get 74*14, and subtract 28 to get 72*13. I don’t generally do that to ‘weird’ numbers, I usually get closer to multiples of 5, 9, 10, or 11. But a computer stores information differently. Perhaps it moves closer to numbers with simpler binary addresses.
minus-squareNatanaellinkfedilinkEnglish3•edit-215 days agoNot, but I’d do 75*10 + 75*4, then subtract the extra. The LLM method of doing it with multiple numbers without proper interpolation though makes it extra weird
But you wouldn’t multiply, say, 74*14 to get the answer.
I might. Then I can subtract 74 to get 74*14, and subtract 28 to get 72*13.
I don’t generally do that to ‘weird’ numbers, I usually get closer to multiples of 5, 9, 10, or 11.
But a computer stores information differently. Perhaps it moves closer to numbers with simpler binary addresses.
Not, but I’d do 75*10 + 75*4, then subtract the extra.
The LLM method of doing it with multiple numbers without proper interpolation though makes it extra weird