Model Preference and Workflow

💬Community

Thursday, January 29, 2026

Users are discussing their preferred Large Language Models (LLMs) for coding tasks, specifically comparing Claude Code and GPT versions, along with their preferred workflows and the convenience of various tools.

12 tweets•130 engagements

@lindsmccallumLindsay McCallum Rémy

On @steipete's workflow: "The real change for me was GPT-5.2. I think it's underrated. I don't know why all these people still use Claude Code. I kind of get it, it's a different way of working. Whatever @OpenAI cooked there is insanely good. Whatever prompt I type gets me the

♥ 48↻ 4

@farzynessFarzad

Cannot be understated how important it is to have Opus 4.5 be your default model for Claude Code. I took one of the suggestions on here to make it so the system smartly chooses between the models based on task (Opus, Sonnet, Haiku), and it's TERRIBLE. If you haven't done so,

♥ 41

@emanueledptEmanuele Di Pietro