Anthropic 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 thought
toynbee @ toynbee @lemmy.world Posts 23Comments 1,956Joined 2 yr. ago
toynbee @ toynbee @lemmy.world
Posts
23
Comments
1,956
Joined
2 yr. ago
The 7 times table is unfriendly?
I love 7 timeses. If numbers were sentient, I think I could be friends with 7.