HNHacker News
TopNewBestAskShowJobs

SilenN

176 karma · joined September 5, 2019

silennai.com github.com/SilenNaihin
submissionscomments
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
I disregard any comments like this one as baseless hate unless given an example or something constructive.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
See what you don't understand is that you need to coordinate the deacon to take the witness out back and talk to the mayor. It's actually quite trivial.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Yes! I went to a meetup for it as well

- https://x.com/silennai/status/1907540814890521023?s=20

- https://x.com/silennai/status/1918166890322784407?s=20

SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
This is probably true and not emphasized enough. Many are making their value judgements with token limits (which is fair, it is expensive).
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Good point. I'll consciously be trying to write more "out of distribution" now.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
I think you read my comment, but you didn't really READ it.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
See

https://news.ycombinator.com/item?id=46685489

https://news.ycombinator.com/item?id=46687347

SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
That section doesn't include a lick of AI writing. One tell (maybe?) is that I switch from past tense to present tense mid sentence.

Either a) I sound like an LLM when I'm writing articles (possible) or b) turing test AGI something something.

Lists point is fair, I did use Claude for formatting. Where did it off put you here?

SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Appreciate it! And agree. I added a longer comment above saying basically this.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Outside of the story at the start I intentionally tried to make it information dense. Would appreciate feedback!
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Would appreciate feedback, see my comment above!
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
What sections where you most off put by?

I used Claude to expand on my ideas for a few of the purely informational things, and for formatting, but this article is largely written by hand.

For example "Interface tests are the ability to know what's wrong and explaining it." is in hindsight a confusing sentence. Many such cases.

SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Try Cursor Composer! It's the most natural transition. Exactly what you're currently doing, but it inserts the code snippets for you from within your IDE.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
How can I improve it in the future? The intention was to start as a story, and become more of a structured guide as you read on.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
The mayor doesn't communicate to the deacon or refiner well enough. Sometimes my polecat acts like a witness so I have to restart it...
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Nothing competes with Opus 4.5 in Claude Code. Codex & Gemini are arguable.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
https://github.com/SilenNaihin
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Yes, the technical preview of Github Copilot. I rounded up.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Agree! Don't let it get too bad. See my other comment on debugging and refactoring being a core part of your workflow.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
^this
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Agree. And with the comments in the thread.

I'll caveat my statement, with AI ready repos. Meaning those with good documentation, good comments (ex. avoiding Chestertons fence), comprehensive interface tests, Sentry, CI/CD, etc.

Established repos are harder because a) the marginal cost of something going wrong is much higher b) there's more dependencies c) this makes it harder to 'comprehensively' ensure the AI didn't mess anything up

I say this in the article

> There's no "right answer." The only way to create your best system is to create it yourself by being in the loop. Best is biased by taste and experience. Experiment, iterate, and discover what works for you.

Try pushing the boundary. It's like figuring out the minimum amount of sleep you need. You undersleep and oversleep a couple times, but you end up with a good idea.

To be clear, I'm not advocating for canonical 'vibe coding'. Just that what it means to be a good engineer has changed again. 1) Being able to quickly create a mental map of code at the speed of changes, 2) debugging and refactoring 3) prompting, 4) and ensuring everything works (verifiability) are now the most valuable skills.

We should also focus more on the derivative than our point in time.

SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
Any suggestions on what to add to answer the question better? I tried to cover this in "Why I switched", "When to use Cursor", and "My current setup" sections.
SilenN··on I was a top 0.01% Cursor user, then switched to Claude Code 2.0
This. Also I'm quoting the email they sent me.
← PreviousPage 2 of 2