top | item 43916365 (no title) johnthewise | 10 months ago A perfect next token predictor is equivalent to god discuss order hn newest lanstin|9 months ago Not really - even my kids knew enough to interrupt my stream of words with running away or flinging the food from the fork. Tadpole9181|9 months ago That's entirely an implementation limitation from humans. There's no reason to believe a reasoning model could NOT be trained to stream multimodal input and perform a burst of reasoning on each step, interjecting when it feels appropriate.We simply haven't. load replies (1)
lanstin|9 months ago Not really - even my kids knew enough to interrupt my stream of words with running away or flinging the food from the fork. Tadpole9181|9 months ago That's entirely an implementation limitation from humans. There's no reason to believe a reasoning model could NOT be trained to stream multimodal input and perform a burst of reasoning on each step, interjecting when it feels appropriate.We simply haven't. load replies (1)
Tadpole9181|9 months ago That's entirely an implementation limitation from humans. There's no reason to believe a reasoning model could NOT be trained to stream multimodal input and perform a burst of reasoning on each step, interjecting when it feels appropriate.We simply haven't. load replies (1)
lanstin|9 months ago
Tadpole9181|9 months ago
We simply haven't.