Jiakai's Blog — Page 3

Tests Grok 4’s X-native search, agent workflow, low censorship, image recognition, Deep Research, and weaker Chinese-language performance.

Evaluates Claude 4 Opus and Sonnet across coding, writing, API access, and Claude Code, then revisits the product after Max-plan use.

Organizes Google I/O 2025’s AI announcements across Gemini, AI Mode, Flow, Veo, Stitch, Chrome, Project Astra, Android XR, and live translation.

Compares ChatGPT o3 and o4-mini through coding, search, image understanding, hallucination, limits, and everyday use after launch.

Deploys Kasm Workspaces for isolated browser sessions, covering persistent profiles, clipboard behavior, resource cleanup, and use with datacenter IPs.