Peter Yang @petergyang

Updated my AI model capabilities table.

Here's my favorite model for each task:

1. Everyday answers: I use ChatGPT because GPT-5 is fast, concise, and almost never hits rate limits.

2. Writing: Claude is my main editor. I give it examples of my best writing and it just gets my voice. This is 80% of my AI usage.

3. Coding: I like Claude Code but some of my friends swear by Codex with GPT-5 high. It's wild how fast OpenAI caught up in AI coding.

4. Deep research: I like Claude because it generates 5-page reports that I'll actually read vs. 30 page essays.

5. Video generation: Veo 3.1 might be the better model but I enjoy Sora more to make videos of my family and friends. OpenAI gets AI + social.

📌 Watch my new video on exactly how I use AI for each task plus Projects and Deep Research:

Oct 29, 2025 View on X →

https://x.com/petergyang/status/1983541902646653150