Hacker News Reader

I think your demo need more realistic thinking logs because thinking usually burns at least 2x to 3x of tokens of the code and for harder tasks much more.

View on HN

Indeed, at 30tok/s make it pause for 20 seconds while "thinking" is streaming (and hidden); that's the real experience.

Yes, it should use actual output from some of the open models.

Reply on news.ycombinator.com