Recent submissions

Comment · 11 days ago
Sounds to me like the models really read Scott Adam’s blog and books, in which he essentially said the same again and again (before he dedicated the end of his life to his tribe). People decide with their gut, are loyal to their tribe, and then invent reasons that sound like they support the fact. That’s why changing someone’s opinion is so hard, and people must be tricked into it by framing the opinion in the right way. Which only a few „master persuaders“ were effective at it, including Donald Trump.
Comment · 3 months ago
That's a bad example: it did not hallucinate about the codebase (which it had access to), but about a rule outside the codebase (which is not in the context, I assume). Yeah, missing requirements can cause it to rely on things it thinks are true. Same as humans do all the time when they lack context.
Comment · 3 months ago
Can you write 10k LOC a day without a coding agent?

It's the same issue. You can walk 100 miles. Just not in a day. And you can create 10k LOC without a coding agent. Just not in a day.

I don't think that coding agents enable technical possibilities. They just allow things that wouldn't be economically possible without them.

Comment · 3 months ago
But you could still arrive if you walk instead of using the bicycle. And I am sure you can do the same stitches by hand, it just takes forever.

Same with coding agents. I could do it by hand. It just would take much longer. Often so long that it would be impractical.

Comment · 3 months ago
Have you really used the latest models (say Opus 4.8+ or Fable)? When was the last time they gave a wrong answer to a question about the code base? Half a year ago that could have happened. But not today.
Comment · 3 months ago
I usually do so I understand what I am replying, but seriously, the latest Opus and Fable versions get it right more often than I would. The time of AI hallucinations is over, as long as they have the context.
Comment · 3 months ago
I did that the first time. But how often do you want to say that (in a public chat that their supervisors can read)?
Comment · 3 months ago
I am a software engineer. Most of the times, the people asking are from product management or devops. Devops contractors are the most difficult ones. They have access to the code, they have access to Claude. But they don't use it.
Comment · 3 months ago
Sometimes I do that. The problem is that it makes them look bad.
Comment · 3 months ago
In my life, the bigger issue are people who are not asking Claude, but asking me.

Because it would take 15 minutes to find out the answer myself, and 3 minutes to let Claude find it, I ask Claude. So how should I answer? Should I disclose that I used Claude to find the answer? Or should I act like I did it myself, appearing to have super-powers that I don't possess?

Comment · 3 months ago
I only see „This deployment is temporarily paused“.
Comment · 3 months ago
Max comment nesting reached. Instead of going through your response one by one, let me just say one thing: the premise and promise of the whole energy transition are based on studies that completely underestimated the physical and engineering challenges in practice. That's why we are where we are. Energy costs have gone up; CO2 emissions have not. I wouldn't believe any study before it has been implemented at scale, at least in a region or small country.
Comment · 3 months ago
Comment · 3 months ago
870 MWh? It would take about 500 of them to make it through a 1-2 week dunkelflaute.
Comment · 3 months ago
How can you be sure of that before even having a practical and proven solution for the required scale of storage?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton