That so weird, it’s seems like everybody here prefers Claude.
I’ve been using Claude and openai in copilot and I find even 4o seems to understand the problem better. O1 definitely seems to get it right more for me.
I’ve been using Claude and openai in copilot and I find even 4o seems to understand the problem better. O1 definitely seems to get it right more for me.
I guess if you don’t need to maintain it, just an ever growing blob of complexity that will be reinvented into new blobs every time when the old one becomes too immobile :)
When I was still subscribing to OpenAI (about 4 months ago) this didn’t exist.
I’ve found using Claude via Copilot in VS Code produces noticeably lower quality results than 3.5 Sonnet on web. In my experience Claude web outdoes GPT-4o consistently.
Sonnet v2 in particular seems to be a bit broken with its reasoning (?) feature. The one where it detects it might be hallucinating (what's even the condition?) and reviews the reply, reflecting on it. It can make it stop halfway into the reply and decide it wrote enough, or invent some ridiculous excuse to output a worse answer. Annoying, although it doesn't trigger too often.