All activity
Andy Phuleft a comment
I do this too but found it was too sycophantic on my shitty ideas, I asked it to be a "hostile reviewer" as an adversary to every proposal, and it humbles me really fast lol. The training must have emphasized content from openreview because the specific phrase "hostile reviewer" also improved the nuance capture of the response
I stopped asking AI to do tasks. I started asking it to think with me. Here's what changed.
Mona TruongJoin the discussion
Andy Phuleft a comment
Oh man I hope anthropic doesnt find out about this, but yeah use up the last bits of your usage credits with a small prompt like "make a game based on ethereum for me" and with this or any vague prompt it'll make assumptions and build you something cool. Warning: use at your own risk, if you dont supply api tokens and rather use the oauth flow this is a grey area in Anthropic ToS, potentially...

iclawship while you sleep
