Posts
All the articles I've posted.
-
GPT Image 1.5 vs Nano Banana Pro: What My Prompts Actually Showed
GPT Image 1.5 tops Image Arena, but X says it’s worse than Nano Banana Pro. I ran identical prompts—illustration, posters, English/Chinese typography, and a TravelBrain itinerary JSON—to see where each model wins.
-
GPT‑5.2-Codex: A Restrained Upgrade With Clearer Priorities
OpenAI’s GPT‑5.2-Codex hits state-of-the-art results on SWE‑Bench Pro and Terminal‑Bench 2.0, improves long-horizon refactors and Windows workflows, and leans hard into defensive cybersecurity.
-
TravelBrain: an offline travel planner built from collected inspirations
Why I built TravelBrain as an offline travel planner where you collect ideas into an inbox, drag them onto a timeline, and build trips like LEGO — all without syncing to the cloud.
-
The Gap Is Widening: What DeepSeek-V3.2 Tells Us About Two AI Futures
DeepSeek's latest paper admits the gap with closed-source models is growing. But the real story is how chip export controls forced two diverging AI paradigms—and what that means for the endgame.