joe8756438

Put another way: “reading code costs the same as it always did” arguably more when you consider that the cost of reading goes down when the ability read goes up. in other words if you wrote the thing it is likely you can read it fast. but reading someone elses stuff is harder.

Interesting. Has anyone found running multiple parallel agents useful in practice?

Is there any marked difference or benefit over Claude Code?

Estimates will continue to go earlier, and more things that were, or are, alive will be considered exceptional. Seems to be a function of looking.

exactly, the real question is what the elves are doing while they’re unseen.

i have a house in a lot of sun in mid atlantic usa. i have spent a modest amount of time casually exploring solar. the cost/benefit never seems that great. what am i missing?

Go on

Currently, the only way to understand code is to read it. You no longer need to understand code to produce it (maybe in some pre-AI cases that was also true).

So no, you don’t _need_ to read code anymore. But not reading code is a risk.

That risk is proportional to characteristics that are very difficult, and in many cases impossible, to measure.

So currently best practice would be to continue reading code. Sigh.

It seems like the archery gets disproportionately more “hollywood doesn’t understand how it works” coverage than other things.

Is that because I’m an archer and that’s what I see?

Projects like this are fascinating for reasons, I guess, unintentional to their creators.

Is what you can see at this level of detail helping anyone understand the painting?

Someone thinks so. So what do we now know?

there is no such bar.

We don’t even have a good way to quantify human ability. The idea that we could suddenly develop a technique to quantify human ability because we now have a piece of technology that would benefit from that quantification is absurd.

That doesn’t mean we shouldn’t try to measure the ability of an LLM. But it does mean that the techniques used to quantify an LLMs ability are not something that can be applied to humans outside of narrow focus areas.

idk, i think it’s as worth mentioning as the writing style, which a lot of the comments are about. and i think they’re fair — don’t mind the style myself

What’s the saying? Twice the work, half the credit?

In all seriousness tho, I don’t buy it. It’s pretty hard to solo-achieve things in most complicated work environments. Saying you’re part of a group effort means more to those more interested in collaboration, good groups know to select on that criteria.

yeah, on a small scale it’s actually pretty easy to make a decent dent in the feed bill. once you get over a dozen hens though it would take a few adults to make enough waste. chickens eat a lot!