News for hackers. Stuff that matters.

A comment on Cerebras achieves 2,500T/s on Llama 4 Maverick (400B). Parent comment

Re:Cerebras achieves 2,500T/s on Llama 4 Maverick (400B) by tiffanyh on Saturday May 31, 2025 @07:50AM (#44143618)
How do you create a prompt for Gemini to spend 200 seconds and review multiple times.

Is it as simple as stating in the prompt:

  Spend 200+ seconds and review multiple times <question/task>
[ Parent | on HN ]
Re:Cerebras achieves 2,500T/s on Llama 4 Maverick (400B) by baq on Saturday May 31, 2025 @05:17PM (#44146973)
You give it a task from hell which the devil himself outsources, like ‘figure out how these fifty repositories of yaml blobs, jinja templates and code generating code generating hcl generating yaml interact to define the infrastructure, then add something to it with correct iams, then make a matching blob of yaml pipelines to work with that infrastructure’
[ Parent | on HN ]