Hacker News: istinetz

New comment by istinetz in "Show HN: ScrapAI – We scrape 500 sites. AI runs once per site, not per page"

istinetz — Tue, 17 Mar 2026 08:49:12 +0000

very neat!

how do you combat silent failures?

for example, I am scraping website A, getting 500+ pdf files; then they change their layout, the ETL breaks, we autoregenerate it with Claude, but then we get only 450 PDFs. The orchestrator still marks it as a successful run, but we get only part of the data.

Or: the ETL for website B breaks. We use our agentic solution, we successfully repair it, and it completes without errors, but we start missing a few fields that were moved in another sub-page.

Did you encounter any such issues?

New comment by istinetz in "Conbini Wars – Map of Japanese convenience store ratios"

istinetz — Mon, 12 Jan 2026 09:29:18 +0000

this is very cool! I love how responsive the interface is.

New comment by istinetz in "Kroger acknowledges that its bet on robotics went too far"

istinetz — Tue, 09 Dec 2025 09:30:58 +0000

judging by his name, he is perhaps in Sofia. I am also living here, and can confirm that many middle class people order groceries online.

New comment by istinetz in "Ask HN: Good Sites for/with AI Enthusiasts?"

istinetz — Mon, 23 Sep 2024 11:46:20 +0000

>It’s also where furkan gets pretty much all his content, before it gets paywalled.

Who/what is Furkan?

New comment by istinetz in "ChessDream, a place for chess players to improve"

istinetz — Wed, 18 Sep 2024 08:34:11 +0000

Ok, if you're just using the lichess puzzles and stockfish, why wouldn't I just go to lichess?

New comment by istinetz in "ChessDream, a place for chess players to improve"

istinetz — Tue, 17 Sep 2024 10:53:25 +0000

yep, the lichess algorithm for finding puzzles from real games is way more sophisticated than this, and they find some really weird bugs

New comment by istinetz in "ChessDream, a place for chess players to improve"

istinetz — Tue, 17 Sep 2024 10:50:46 +0000

feedback - I tried the puzzles. 1) they all seem trivial and don't escalate in difficulty fast enough 2) I got stuck on the 14th - I'm making the correct move, but nothing happens. I'm not wrong, but even if I were wrong, the website ought to have some feedback to show me my move is wrong, or an option to give up.

New comment by istinetz in "Anarchy in Sudan has spawned the world’s worst famine in 40 years"

istinetz — Sun, 01 Sep 2024 15:50:21 +0000

If you don't want your opinion to be critiqued, you can simply not post.

New comment by istinetz in "Show HN: Similar user search for Hacker News"

istinetz — Sat, 31 Aug 2024 06:52:25 +0000

Dude?

New comment by istinetz in "Researcher finds flaw in a16z website that exposed some company data"

istinetz — Sun, 21 Jul 2024 01:27:56 +0000

I have literally seen EU institutions fragrantly break GDPR

New comment by istinetz in "Researcher finds flaw in a16z website that exposed some company data"

istinetz — Sat, 20 Jul 2024 16:20:41 +0000

>Implying the Eu will actually do anything at all whatsoever upon reporting a gdpr issue

>Money is something VCs “print” and manipulate.

You wot m8

New comment by istinetz in "ChatGPT is biased against resumes with credentials that imply a disability"

istinetz — Sun, 23 Jun 2024 08:10:11 +0000

There is a slight difference between glasses and hiring someone actually disabled - blind, deaf, can't do physical labor, autistic, etc.

Yes, you can try to assert fuzzy boundaries, but that doesn't mean that the thing we're pointing to doesn't exist. There are actually plenty of people that cannot do plenty of jobs.

Nobody minds hiring a software dev with a wheelchair or a person wearing glasses. This is not objectionable. Your proposed way to view this dilemma has to also be able to address the more problematic cases - what happens with an Amazon worker who can't stand up for longer periods of time? Or a blind person applying to be a QA?

New comment by istinetz in "Smoking weed every day makes me less presentable and less productive. I love it"

istinetz — Wed, 29 May 2024 16:16:30 +0000

https://trends.google.com/trends/explore?date=all&q=Normie

New comment by istinetz in "The Death of a Mnemonist"

istinetz — Mon, 13 May 2024 11:11:28 +0000

>On the flip side, I haven't found any practical use for this ability either.

well, you can reliably trick a polygraph

New comment by istinetz in "Adaptive RAG – dynamic retrieval methods adjustment"

istinetz — Mon, 01 Apr 2024 15:43:11 +0000

yes - private data, real-time data, curated data, citations with no hallucinations, RAG on tabular data, RAG on video, RAG on hierarchical mixed data, RAG over a graph

New comment by istinetz in "Show HN: Forest Watch"

istinetz — Wed, 06 Mar 2024 18:37:04 +0000

I want to help increase the coverage, what can I do?

New comment by istinetz in "No "malfeasance" behind Sam Altman's firing, OpenAI memo says"

istinetz — Sat, 18 Nov 2023 22:59:11 +0000

The primary purpose of a company is not to take care of employees. It is to make money by providing valuable services to society.

Yes, it is good governance to cut unproductive jobs.

New comment by istinetz in "FBI Crime Data Explorer"

istinetz — Sun, 12 Nov 2023 15:59:30 +0000

> This requires ignoring socioeconomic status

Finding holds if you control for SES.

New comment by istinetz in "What do I think about Community Notes?"

istinetz — Wed, 16 Aug 2023 13:22:44 +0000

A lot of assertions, zero evidence.

Can you give us some examples of bad Community Notes?

New comment by istinetz in "What do I think about Community Notes?"

istinetz — Wed, 16 Aug 2023 10:27:45 +0000

[This community note is rated as very helpful and low polarity.]