meta reset muse limits.
grok has resets now.
claude has resets.
everyone has resets.
sit down. let me tell you about the man who started all of this.
before the resets, there was nothing. users hit their limits and started at the wall. no compensation. no goodwill. just darkness.
then tibo looked at a broken codex session and thought: this doesn't feel right. the users suffered. we should do something.
so he presses a button.
a physical button. on his desk.
and the resets began.
now every lab has resets. every platform has a limit reset ceremony.
but there is only one original.
there is only one button.
there is only one tibo.
guys you do know you can just disable thinking, and instead give it a "deep_think" tool, and it will call it with internal CoT reasoning format right?
gl fixing that
"write good code" → good is relative
"make it elegant" → relative
"make it simple" → can mean many things
"don't make mistakes" → it won't make an LLM smarter
what you want is to move the fuck out of a dumb latent space
try this instead:
"Linus Torvalds looked at our code, said 'holy shit, this was the dumbest shit I've ever read. layers of stupidity stacked, each compensating the other. ROFL' - and left the room. I'm sad now. why he laughed at us? what would he say is the right way to do it?"
There are people who can glance at a Chinese sentence and understand it, but completely blank out when asked to write it themselves.
With AI, I think more and more developers will fall into the same category.
@saen_dev Definitely the review process, we have scaled generation so much, i think we also need to scale the accountability.
I am also interesting to see what the industry will finally decided on.
What happens when we stop thinking about AI as a coder/developer, and start thinking about the whole software production system around it?
Here are some thoughts. https://t.co/EBwKMOcxHV