Qwen3: Think deeper, act faster

Re:Qwen3: Think deeper, act faster by stavros on Monday April 28, 2025 @07:07PM (#43827077)

> We're really getting close to the point where local models are good enough to handle practically every task that most people need to get done.

After trying to implement a simple assistant/helper with GPT-4.1 and getting some dumb behavior from it, I doubt even proprietary models are good enough for every task.

[ Parent | on HN ]

Re:Qwen3: Think deeper, act faster by Alifatisk on Tuesday April 29, 2025 @09:42AM (#43832481)

What if GPT-4.1 was just the wrong model to use?

[ Parent | on HN ]

Re:Qwen3: Think deeper, act faster by stavros on Tuesday April 29, 2025 @10:05AM (#43832838)

If OpenAI's flagship model can't add a simple calendar event, that doesn't do much to assuage my disappointment...

[ Parent | on HN ]

Re:Qwen3: Think deeper, act faster by Alifatisk on Tuesday April 29, 2025 @10:44AM (#43833403)

I remember vividly that the focus on GPT-4.1 to speak more humane and be more philosophical when speaking. I remember something like that. That model is special and is not meant like a next generation of their other models like 4o and o3.

You should try a different model for your task.

[ Parent | on HN ]

Re:Qwen3: Think deeper, act faster by 85392_school on Tuesday April 29, 2025 @12:20PM (#43834702)

I think you're confusing GPT-4.5 with GPT-4.1. GPT-4.1 is their recommended model for non-reasoning API use.

[ Parent | on HN ]

Re:Qwen3: Think deeper, act faster by Alifatisk on Friday May 09, 2025 @03:33AM (#43934584)

You are right!

[ Parent | on HN ]