anton@abacaj

3 years ago

I don’t see how OpenAI survives on gpt-3.5 and gpt-4. Literally gpt-3.5 is utterly useless in the presence of Claude haiku

Ruben Hassid@RubenHssd

3 years ago

I wanted to test claude-haiku vs. gpt-3.5. I ended up showing haiku is better than gpt-4 at writing & following guidelines. Read my entire benchmark below. #1 → a zero-shot prompt: https://t.co/wv5TO3UQmw

Larry Sanger@lsanger

3 years ago

OpenAI says GPT-4.5 or even GPT-5 might arrive by this summer. https://t.co/hQCFu2PqFX But I'll tell you something. I think a better version might already have been advanced. I have just one piece of evidence, but it's pretty persuasive. 👇