Sentient OS local LLM for Mac email
Sentient OS (YC F26) is out and the pitch is the part I keep rereading: an LLM living on your Mac, not in a datacenter. Double tap Command and a reply gets drafted for you. The trick is that it spends the night picking up how you write and what you've been talking about, so the draft comes back in your voice instead of bot voice. Which matters when the morning starts with 15 emails sitting there and the old answer was 40 minutes of straight typing. No cost attached to each message, nothing routed through a cloud, and on-device inference without a cap. That efficiency jump is the insane bit
