I worry most about blindspots with this kind of approach. Let's say that this repository goes on for years, at which point the docs folder is several MB in size. Would Codex be able to think outside of the box? Or would the aggregate of the Markdown content fundamentally cover enough ground to prevent it from thinking of novel new approaches to existing problems?
I feel that AI doesn't necessarily replace my thinking, but actually helps to explore deeper - on my behalf - alternative considerations in the approach to solving a problem, which in turn better informs my thinking.
I asked it to build me a weather machine and it's responding to me like a teenager.
AI:
Authentication successful! Go back to the webpage to continue.
Me:
Hey!
AI:
yooo whats good!! u got any weather stuff u wanna chat about or just saying hi?
Me:
how’s the weather in New York City
AI:
ohh nah i don't have real-time data so i can't tell u the actual conditions rn! but if u check like weather.com or just search "nyc weather" u'll get the live stuff instantly
tho if u tell me whats goin on there rn i can get HYPED abt the atmospheric conditions!! like is it humid?? what's the pressure doin??
My wife and I are in the market for a new refrigerator and we have never heard anything good about Samsung. I was at least expecting different "tiers" to have different reputations, but no, it's the entire _brand_ that is bad. Parts getting defective within the first few years, low quality materials, and now this? No thanks.
I appreciate how in the YouTube video on the repo's README, his cat walks right on top of his project, and he doesn't even react at all. The cat just gets out of the way all by itself. But I guess it _had_ to be part of the clip, heh.
272 layers in a single image seems really unusual, is that just due to my lack of experience with containers? I've never seen an image with more than maybe a few dozen in my career...