Viewing profile — paretolaw

My every 2nd prompt became ctrl+c and typing "tell me why you did that!" Claude.md just keeps growing and having less effect...

My 2 cents Dont listen salesman talking about engineering. Unless he has credibility proven by things he had done recently. Person might be zillionare but he cant buy credibility.

Pen and paper design and thinking, then writing it down once I am home

Buzzword over buzzword, looks like just another LLM client

Would need to try out in a complex project to have opinion. However I already see few problems. Slower development due this loop of generating code from you mini spec. I would snap…

Writing fizzbuzz requires that you understand algo + you credit card, while agent requires only your credit card. I believe most of people will pick the 2nd one.

Just another CLI? You could simply fork one existing, rename it, and save tokens

I might be late to the discussion, or someone already wrote this. If so, let me know and I’ll delete the post. He might be right in his context, but there is no silver bullet. Some…

I dont care who/what wrote it, all until it good work. You are free to spend 10 hours on agents rules/constraints/... and then tell them to write it, or write it by yourself. Whate…

This started for me since opus 5... To see that it works you first need to be some famous "programmer" who is on someone's payrole, basically doing their marketing.

Why does it matter if code is written by LLM?

Why does it matter? "Tainted by AI" seems like a cool proxy measure for something that is already measured by some existing measures.

What is purpose of private messenger if your OS (Android) and hardware is likely compromised.

So many problems, beautifully entangled and solved together. I prefer KeePass: it does one thing and does it well. Sharing passwords across multiple devices was never really a prob…

If and only if that is actually true, then perhaps nothing matters. Until then, calling out shenanigans remains a noble art.

Isn’t an estimate supposed to be off? The real question is: how much effort is worth spending to make it less wrong? Improving an estimate has a cost, and sometimes it’s more effic…

I have the opposite experience. AI hasn't made weak engineers less harmful. It has made their output more plausible, which can make it more expensive to deal with. I now spend a lo…