Comment by hmottestad
1 year ago
I’ve been using Claude 3 Opus for a while now and was fairly happy with the results. Wouldn’t say they were better than GPT-4, but considerably less verbose which I really appreciated. Recently though I ran into two questions I had that Claude actually answered incorrectly and incompletely until I prompted it. One was a Java GC questions where is forgot Epsilon and then hallucinated that is wasn’t experimental anymore. The other was a coding question where I know there wouldn’t be a good answer, but Claude kept repeating a previous answer even though I had twice told it that it wasn’t what I was looking for.
So I’ve switched back to GPT-4 again for a the time being to see if I’m happier with the results. I never felt that Claude 3 Opus measurably better than GPT-4 to begin with.
I just run a system message around my coding exercises to provide minimal explanations and be concise.
Same here -- one or two sentences along those lines in GPT-4's system prompt makes a _world_ of difference.
Agreed and from a pure ChatGPT perspective the way to go is creating your personal "GPTs" (I hate the name of the product) that are simply system message wrappers. So I will have a Coding GPT, and email GPT etc.