Rant: Everyone keeps calling the new Claude model 'just a bigger GPT' and it's wrong

I keep seeing posts that treat Claude 3.5 Sonnet like it's only about having more parameters than GPT-4. The real innovation is its reasoning on complex, multi-step tasks, like coding a full web app from a single prompt. I tested it on a project in Denver last week and the difference was clear. Has anyone else actually compared them on something hard?

1 comments

1 Comment

cole3561h ago

Had it write a whole data pipeline last month. The way it handled the edge cases was just cleaner than GPT's output. Felt like it actually understood the dependencies.