My Model Stack After the Wildest 8 Days in AI: Opus 4.5: Most daily...

@mattshumer_
Matt Shumer@mattshumer_
45 views Dec 01, 2025 ~1 min read
Advertisement
1
My Model Stack After the Wildest 8 Days in AI:

Opus 4.5: Most daily code tasks where I know how I want the model to do what I want. Fast, clean, reliable, but often starts writing code before it grabs all the context it needs (measures once, cuts twice).

Codex‑Max: Larger, more difficult code tasks (especially backend) where I don't want to prescribe the best way to do something. Explores before it acts, so it's often more reliable (measures twice, cuts once).

GPT‑5.1 Pro: Deep planning, research, high-stakes work (again, especially backend) where I can't afford to be wrong. If I don't want to have to deal with correcting subtle mistakes, I reach for GPT-5.1 Pro. It just gets things right the first time (but it's super slow, and stuck in the ChatGPT interface).

Gemini 3 Pro: Writing, general reasoning, and UI design. Best at making frontends look polished rather than like AI slop, but less reliable than others on general code tasks.
2
I'll be sharing a more detailed blog post on this soon.

If you want to be the first to see it, go here: tally.so/r/w2M17p
Actions
What You Can Do
  • Export as PDF or Markdown
  • Batch Export to Notion
  • Bookmark & Highlight
  • Screenshot Tweet
Create Free Account

Includes 7-day Premium trial

Advertisement