Viewing profile — km144

The entire ecosystem of CC is designed to facilitate burning tokens. You have to ask the LLM to write a script for the app to tell you which folder you're working in and which bran…

What output style have you found to actually fix Opus 5's grating prose then? I find it leans hard into its preferred grammatical structures and rote sayings no matter what I inclu…

> because it's really hard to learn anything by skimming code that's being pooped out by Claude. I think this is pretty dubious. It's true that you have to do more proactive learni…

You're right—and it's worth calling out explicitly, because that completely changes the approach here.

Here is one data point for cost: https://artificialanalysis.ai/models?cost=intelligence-vs-co... Here is another data point for output token efficiency: https://artificialanalysis.…

I agree, very odd they did not comment on any theories for the degradation here. Dip and then rebound at max effort is pretty interesting too. Overthinking is bad, but you can over…

> So I would rather share a match with the occasional cheater than run un-auditable ring-0 software on the same machine I use for anything private. The article makes an argument th…

I'm basically restating what you said, but it's amazing to me that the vast majority of people you will meet, even educated people, are casual dualists and free-will libertarians. …

Because, as the OP said, working hours are powered by norms. There are salaried positions and companies and teams that certainly will make you work 6 days a week, or make you feel …

[dead]

The real question is: Why are people designing benchmarks that, if a model is trained on them, it won't improve the performance of the model at any real-world tasks? Why would anyo…

But there is a way for even an aligned federal government to fight back against the slide into authoritarianism, even with an authoritarian president expanding the powers of the ex…

> “In my trips to Wall Street,” Dyer told the panel, “one of my analyst friends took me to lunch one day and said, ‘Joe, you have to get iRobot out of the defense business. It’s ki…

Sure, but the author is arguing that the outcome you're describing is tightly coupled to the perverse incentives that he describes in the article. Investors pushed the company towa…

I'm not so sure I buy the premise that engineers are really dismissing AI because it's still not good enough. At the very least, this framing does not get to the heart of why certa…

Low mileage used cars don't come with a warranty, or probably have a more limited warranty if they're CPO. Leases can be better, but again they are usually better choices in high d…

Have you seen the prices of pre-owned Honda/Toyota sedans that are less than 5 years old? There are absolutely cars out there where trading in your new car after 3-4 years can make…

Those things also require more willpower than taking a medication. Willpower is generally determined by your particular psychology which is determined by genetics and environmental…

"Real industry" also has quite a hard time getting things done these days. If you look around at the software landscape, you'll notice that "getting things done" is much easier for…

I think the problem is false positives, not false negatives. The people you interact with during the interview process have all sorts of reasons to embellish the experience of work…

You hit the nail on the head. There is no place on the internet more broadly susceptible to the same kinds of "founder brain" malaise that has afflicted so many in Silicon Valley--…

Maybe it that's an apt analogy in more ways than one, given the recent research out of MIT on AI's impact on the brain, and previous findings about GPS use deteriorating navigation…

I think it's a bit fallacious to imply that the only way we could be in an AI investment bubble is if people are reasoning incorrectly about the thing. Or at least, it's a bit redu…

> According to this view, justice demands that variations in how well-off people are should be wholly determined by the responsible choices people make and not by differences in th…

As you alluded to at the end of your post—I'm not really convinced 20k LOC is very limiting. How many lines of code can you fit in your working mental model of a program? Certainly…