Press Space to continue
Curated tech posts from X on AI, startups, and product development—signal without the doomscroll, updated on weekdays.
Press Space to continue
Press Space to continue
Gemma 4 E4B on my iPhone gives a sense of why Apple thinks Gemini on-device models might be their solution. Very fast, GPT-4ish performance. Some agent work with harness. Skills implementations. Really impressive But it still has the problems of small models: fragility & errors