[stuckinhell]

I've had way better success with GPT-4o than claude. I wonder why

[netsec_burn]

Have you tried 3 Opus or 3.5 Sonnet? Are you using it for programming, or something else?

[stuckinhell]

everything really. just opus so far

[simonw]

Personal prompting style, I imagine,

[Workaccount2]

People really, really, underestimate how important prompting is.

I would be confident in stating that half the people who complain about a model are actually just suffering from poor prompting.

[prng2021]

And what makes you so confident that all those people are using different prompt styles when comparing models? You think most people don’t even understand the bare basics of how to compare two products?

[simonw]

That's the point: maybe someone has a personal prompting style that works great with Claude but gives worse results with GPT-4.

They might complain that GPT-4 is rubbish in comparison to Claude, but someone with a different personal prompting style might experience the opposite.

[wiether]

Having a prompting style that works with a model but not quite with another is much different than "suffering from poor prompting" the previous person was accusing others.

And given that those are tools, it's more like "the model can work with the user's prompts" rather than "the user's prompts are adapted to the model".

Unless we're here for an ego trip.

[prng2021]

Ah, I see. I’d be interested to see a study on that. I find it hard to believe it would make such a stark difference but it’s possible.

[SSLy]

are non-snake oil prompting techniques described anywhere?

[simonw]

Those are hard to come by, but the Anthropic prompting documentation is a pretty great source: https://docs.anthropic.com/en/docs/build-with-claude/prompt-...