Hacker News: ashu1461

New comment by ashu1461 in "Voxtral Transcribe 2"

ashu1461 — Thu, 05 Feb 2026 08:20:04 +0000

Wondering if most of the AI agents use real time apis or transcription apis.. anyone had experience with building voice agents can comment ?

New comment by ashu1461 in "When internal hostnames are leaked to the clown"

ashu1461 — Thu, 05 Feb 2026 08:16:54 +0000

Isn't the article over emphasising a little bit on leakage of internal urls ?

Internal hostnames leaking is real, but in practice it’s just one tiny slice of a much larger problem: names and metadata leak everywhere - logs, traces, code, monitoring tools etc etc.

New comment by ashu1461 in "Don't rent the cloud, own instead"

ashu1461 — Thu, 05 Feb 2026 08:10:17 +0000

And not just any FTEs, probably few senior / staff level engineers who would cost a lot more.

Show HN: AI powered Hacker News reader

ashu1461 — Thu, 08 Jan 2026 14:22:10 +0000

I built an alternative Hacker News reader focused on quickly scanning posts and understanding what they are about before clicking through.

Things I felt were missing in my own HN reading experience :

- Scanning information quickly if I have limited time and don't want to spend time reading the whole articles.

- Sometimes I don't want to read the full article. I just want to understand the gist first and then decide whether it's worth going deeper.

- Adjusting to every authors writing style / navigating to there website also takes extra mental effort.

- I want to easily be able to brainstorm articles with a LLM, for example by having it explain or simplify the article for me

- Filtering on the basis of topics, Example if I am not interested in hardware articles, would like to skip them (Feature is WIP)

I also got a chance to explore new technologies while building it.

I choose svelte kit over react / next and cloudfare hosting over firebase / vercel

Right now I am improving the AI summarisation experience in places where the page is under a paywall.

I'd love feedback on where this helps and what can be improved.

Comments URL: https://news.ycombinator.com/item?id=46541285

Points: 4

# Comments: 2

New comment by ashu1461 in "The Showa Hundred Year Problem"

ashu1461 — Mon, 05 Jan 2026 09:45:27 +0000

Reminds me of the year 2038 problem, which will be more scary than this.

So if you are storing epoch time (no of milli seconds after 1970) in integer variables, your code will most probably break, which I feel is going to happen in a lot of scenarios.

New comment by ashu1461 in "The unbearable joy of sitting alone in a café"

ashu1461 — Mon, 05 Jan 2026 09:39:51 +0000

Meditation used to need a cave or a mountain, now it just needs a cafe and no phone.

New comment by ashu1461 in "During Helene, I just wanted a plain text website"

ashu1461 — Mon, 05 Jan 2026 09:15:18 +0000

Google also used to have a go app which they deprecated later on, while now i think about it what is the use of having a go app, if the websites which are shown in search results are not optimised for slower networks.

New comment by ashu1461 in "Show HN: Terminal UI for AWS"

ashu1461 — Mon, 05 Jan 2026 09:02:31 +0000

I had the same doubt. With CLIs you can make your own custom shortcuts, LLMs can use it to get things done for you as well. With TUIs I think either these are hobby projects or meant for people who are obsessed with speed.

Though speed impacts are also something which I am uncertain about. Comparing Vim with IDEs, for sure there will be few things which are faster in vim but decent no of things which can be done faster in an IDE as well, so can't comment on your overall speed gains.

New comment by ashu1461 in "Amazon will allow ePub and PDF downloads for DRM-free eBooks"

ashu1461 — Fri, 19 Dec 2025 14:05:30 +0000

Amazon used to be really customer centric 5-10 years ago, I remember once I ordered a physical book which was late in delivery and I urgently needed that book, so they gave me a free kindle edition till the book got delivered.

New comment by ashu1461 in "The HTTP Query Method"

ashu1461 — Sun, 30 Nov 2025 03:23:16 +0000

or get requests with query params already handles this in majority of the cases, unless the query size is too big (which ideally should not be the case since in the end it is a get request)

New comment by ashu1461 in "Dilution vs. Risk taking: Capital gains taxes and entrepreneurs"

ashu1461 — Sun, 30 Nov 2025 01:51:37 +0000

This theory seems to be BS, If let us say a founder is raising a seed round of 2m at 20m valuation, then according to hypothetical accrual tax rate, they would need to pay a tax of ~ 3-4m.

New comment by ashu1461 in "Student perceptions of AI coding assistants in learning"

ashu1461 — Sat, 29 Nov 2025 21:14:59 +0000

Google is successful and it's page rank algorithm also does not deliver correct results all the times.

New comment by ashu1461 in "Be Like Clippy"

ashu1461 — Sat, 29 Nov 2025 21:06:01 +0000

Yes if Clippy was released in 2025, it would surely be stealing your data without thinking twice.

New comment by ashu1461 in "All it takes is for one to work out"

ashu1461 — Sat, 29 Nov 2025 20:55:03 +0000

Is it ? In gambling your odds are fixed, but in real life, wouldn't you get better at solving problems with each iteration ?

New comment by ashu1461 in "It's Always the Process, Stupid"

ashu1461 — Sat, 29 Nov 2025 15:48:47 +0000

I think there is one counter argument, LLMs are speeding up everything, including the speed of learning, which also implies that companies that might have bad processes would learn and move to good processes as well on the way.

Example, one of many things, in our SDLC process, now we have test cases and documentation which never existed before (coming from a startup).

New comment by ashu1461 in "It's Always the Process, Stupid"

ashu1461 — Sat, 29 Nov 2025 15:46:23 +0000

Probably the OP might have used LLM's to structure the document, but the sentiment `Automating stupidity = faster stupidity` is a great take away.

Ask HN: What's on your vibe coding roadmap?

ashu1461 — Tue, 14 Oct 2025 21:13:18 +0000

I am thinking of building a LLM based auto correct feature which corrects grammar and auto corrects as I type, pretty much like grammarly but more llm powered and hosted locally.

What's the next thing you're vibe coding or planning to build?

Comments URL: https://news.ycombinator.com/item?id=45584989

Points: 4

# Comments: 4

Ask HN: What is in your vibe coding list

ashu1461 — Tue, 14 Oct 2025 20:59:52 +0000

Comments URL: https://news.ycombinator.com/item?id=45584792

Points: 1

# Comments: 1

New comment by ashu1461 in "SEO Analysis of the top AI startups by A16Z"

ashu1461 — Fri, 03 Oct 2025 22:47:16 +0000

If having a strong SEO strategy was worth 100 points two years ago, how many points would you assign to it in today’s environment? Has its importance increased, decreased, or shifted in nature ?

New comment by ashu1461 in "PEP 810 – Explicit lazy imports"

ashu1461 — Fri, 03 Oct 2025 20:42:25 +0000

Understood make sense