Hacker News: luckilydiscrete

New comment by luckilydiscrete in "CursorBench 3.1"

luckilydiscrete — Thu, 02 Jul 2026 07:57:59 +0000

insert obama medal meme

New comment by luckilydiscrete in "The gauge broke: devs felt 20% faster with AI, measured 19% slower"

luckilydiscrete — Thu, 02 Jul 2026 07:21:59 +0000

https://www.faros.ai/blog/ai-software-engineering

The actual study with the data, minus the "I was right all along" commentary

Show HN: Disposable public file links directly from your machine

luckilydiscrete — Tue, 17 Feb 2026 18:02:09 +0000

I liked magic wormhole a lot but it was inconvenient to ask people to install something to receive a file, and I wished I could just give them the link, so I made the utility to do it.

Comments URL: https://news.ycombinator.com/item?id=47050675

Points: 2

# Comments: 0

New comment by luckilydiscrete in "Don't fall into the anti-AI hype"

luckilydiscrete — Mon, 12 Jan 2026 05:16:21 +0000

It's a combination of being bad at prompting and different expectations from the tool. You expect it to be one shot, and then rewrite things that don't match up to what you want.

Instead I recommend that you use LLMs to fix the problems that they introduced as well, and over time you'll get better at figuring out the parts that the LLM will get confused by. My hunch is that you'll find your descriptions of what to implement were more vague than you thought, and as you iterate, you'll learn to be a lot more specific. Basically, you'll find that your taste was more subjective than you thought and you'll rid yourself of the expectation that the LLM magically understands your taste.

New comment by luckilydiscrete in "Anthropic blocks third-party use of Claude Code subscriptions"

luckilydiscrete — Fri, 09 Jan 2026 06:22:15 +0000

I'll say "maybe-sometimes works" is a misunderstanding.

It feels like that initially, but that's no different from any new tool you adopt. A jackhammer also "maybe-sometimes works" as a hammer replacement.

New comment by luckilydiscrete in "Anthropic blocks third-party use of Claude Code subscriptions"

luckilydiscrete — Fri, 09 Jan 2026 06:18:26 +0000

AI is indeed just hype in a lot of cases, but also has revolutionary value in a other cases. Trying it is the only way you'll be able to differentiate the latter from the former.

New comment by luckilydiscrete in "Show HN: Patchwork – Open-source framework to automate development gruntwork"

luckilydiscrete — Mon, 29 Jul 2024 08:02:49 +0000

While true in a subset of problems, linters will also miss stupid mistakes because not everything is syntactical.

AI for example can catch the fact that `phone.match(/\d{10}/)` might break because of spaces, while a linter has no concept of a correct "regex" as long as it matches the regex syntax.

I don't think anyone is arguing that replacing linters with AI is the answer, instead a combination of both is useful.