Hacker News new | ask | show | jobs
by willahmad 244 days ago
None is comparable to GPT-5 or Sonnet 4.5 experience
2 comments
elzbardico 244 days ago
Frankly, right now I am way more satisfied with qwen-3-coder-420 using Cerebras inference than with those more powerful models.

Inference speed and fast feedback matter a lot more than perfect generation to me.

link
mertbio 244 days ago
Yet.
link