Is the stakes and the ownership. 5 people in a coffee shop working on a 0-1 problem is a lot more stimulating than 90 people on a team shipping incremental updates to a legacy system.
> This is still true - a compiler can never win this battle. All a human programmer has to do is take the output of the compiler and make a single optimisation, and he/she wins. This is the advantage that the human has - they can use any of a wide variety of tools at their disposal (including the compiler), whilst the compiler can only do what it was programmed. The best the compiler can hope for is a tie.
I really love this project and want to keep rooting for its success. But the presentation is currently very confusing. The biggest issue is that I can’t tell what is fictional 'lore' and what is an actual feature of it. I don’t think you have to sacrifice the concept to make things clearer; it’s definitely possible to maintain a strong concept while ensuring visitors aren't lost. Anyway, I hope this goes well!
I am implementing a diagnostic mode that will toggle the tools and story on and off. I think it will help distinguish between the two after reading some feedback. Thanks for your input. I will resolve this gap.
How about adding these texts and reactions to LLM's context and iterating to improve performance? Keep doing it until a real person says, 'Yes, you're good enough now, please stop...' That should work.
An AI can not meaningfully say "thank you" to a human. This is not changed by human review. "Performance" is the completely wrong starting point to understand Rob's feelings.
They say no childbirth means no children. But must children be such an inconvenience? Even if Korea ceases to produce human infants, AI children may be born in their stead. Or, through reverse-aging, the elderly could become the new children.
reply