new | show | ask | jobs Github

John7878781 2 hours ago

In my experience, Gemini excels at explaining new concepts clearly and intuitively. Much more so than other models.

▲

zorked 2 hours ago | parent | next [-]

Gemini is the best general-purpose model. We hear a lot about the other ones here because we are focusing on coding.

▲

pasharayan 28 minutes ago | parent | prev | next [-]

I wonder how much is due to their investment in notebook LLM + gmail work

▲

inbx0 2 hours ago | parent | prev [-]

So, given that developers these days mix and match models anyway with harnesses like Pi, has anyone tried letting Claude or GPT do the coding, and Gemini do the comments and documentation? Maybe even asking it to "translate" Claude's output messages to better human language for the developer or subagents?

	▲	SturgeonsLaw 2 hours ago \| parent \| next [-]
		I use Qwen/Claude for coding and Gemini/Gemma to draft text intended for a human. To me that feels like each model playing to their strengths.
	▲	pkulak 2 hours ago \| parent \| prev [-]
		Seems reasonable. You could just switch the model after the code is written, when you need to ask questions. You’ll lose your token cache, but that’s it.