Vikas

One thing that makes me feel that code factory has not arrived yet is the following experiment: 1.Ask a LLM to do an in-depth rigorous review of your code 2. In a new thread, as same/different LLM to consider those review comments independently and address issues it agrees with 3. Keep repeating until no new concerns I find that this loop always goes on for a ridiculously long time, which means that there is a problem with the notion of claude-take-the-wheel. This seems to happen no matter the harness or the specificity of the specs. It works fine for simple applications, but in the limit if the LLMs have this much cognitive dissonance you cannot trust it. Either this, or LLM are RLHFd to always find some kind of issue.

Dear “15-18 yo founder”s sending me DMs, don’t. Go and hug your parents, fall in love, eat chocolate cereal for breakfast, read poetry. Nobody will give you back these years. And sure, do your homework and learn math and code if that feels fun. But stop building SaaS and hustling. Even if career is what you are optimizing for, this is not the way. You need deep education that will withstand automation. You need to sit with linear algebra and probability theory and philosophy and literature. It won’t get you go viral on X but it’ll make you whole. And mute all the SF performative assholes. Oooops sorry this last one was a note to self.

I wonder what's the smallest amount of today's knowledge you'd need to give to the Romans back in 27 B.C. in order to spark industrialization/modernity roughly equivalent to our own but two millennia earlier

Why is KL Divergence a more commonly used term in the ML literature than the (in my opinion) much more intuitive “relative entropy”?

i feel intense pang of nostalgia thinking about how i will never have to write an immense amount of repetitive code to eg build a website ever again. there was a quiet bluecollar satisfaction to this type of work, knowing that if you don’t stay up all night smacking keys the thing really just won’t exist