alt Hacker NewsIn a not-too-distant future (5 years?) small LLMs will be good enough to be used as generic models for most tasks. And if you have a dedicated ASIC small enough to fit in an iPhone, you have a truly local AI device with the bonus point that you get something really new to sell in every new generation (i.e. acces to an even more powerful model)
Replies
throwthrowuknow • yesterday at 4:59 PM
it doesn’t need to go in the phone if it only takes a few milliseconds to respond and is cheap
➕ show 2 replies
The Taalas approach is much more expensive than the NPU that phones already have.