Hacker News: sunshadow

New comment by sunshadow in "GitHub Copilot: The Agent Awakens"

sunshadow — Thu, 06 Feb 2025 17:43:47 +0000

Too late, we all went to cursor.

New comment by sunshadow in "Neuters: Lightweight front end to Reuters News"

sunshadow — Mon, 30 Dec 2024 10:34:59 +0000

I can make this in couple of weeks, but I need an incentive other than just having fun

New comment by sunshadow in "Neuters: Lightweight front end to Reuters News"

sunshadow — Mon, 30 Dec 2024 10:02:05 +0000

What made you use caddy in front of tiny-http? I guess tiny-http should be still fine on its own. genuinely curious

New comment by sunshadow in "Niantic plans a “Large Geospatial Model” trained on Pokémon Go player data"

sunshadow — Thu, 21 Nov 2024 04:17:43 +0000

They made 11B$ last year. It has incredible amount of ads. If you haven't noticed, then that means they did a great job. (tip: look for the custom logo pins in the map. Its printing money)

New comment by sunshadow in "Winamp Legacy player source code"

sunshadow — Tue, 24 Sep 2024 16:09:20 +0000

According to the license, this repo is not that different than me just extracting the source code from the binaries. Pass.

New comment by sunshadow in "Cloudflare's new marketplace lets websites charge AI bots for scraping"

sunshadow — Mon, 23 Sep 2024 16:14:14 +0000

There is no difference between this and a well known bot prevention mechanism, from the scraper perspective.

New comment by sunshadow in "Web scraping with GPT-4o: powerful but expensive"

sunshadow — Tue, 03 Sep 2024 05:39:53 +0000

I don't see any difference than browserless?

New comment by sunshadow in "Fireworks: Function Calling Model and API"

sunshadow — Thu, 21 Dec 2023 10:41:49 +0000

If you're looking for open-source function calling: Checkout Functionary: https://github.com/MeetKai/functionary/

It's MIT licensed. Supports both CPU and GPU

New comment by sunshadow in "Fireworks: Function Calling Model and API"

sunshadow — Thu, 21 Dec 2023 10:40:30 +0000

Yes, Functionary: https://github.com/MeetKai/functionary/ MIT Licensed

Its actively maintained as open-source. You can even run it with llama.cpp

New comment by sunshadow in "Show HN: Tiny LLMs – Browser-based private AI models for a wide array of tasks"

sunshadow — Thu, 16 Nov 2023 22:07:29 +0000

Original project: https://github.com/xenova/transformers.js

New comment by sunshadow in "Show HN: Flyscrape – A standalone and scriptable web scraper in Go"

sunshadow — Sat, 11 Nov 2023 17:52:32 +0000

Unless you start a war against scrapers, you don't need to worry about that as I'll always find a way to scrape your site as long as its valuable to 'me'. Even if it requires Real browser + OCR :)

New comment by sunshadow in "Show HN: Flyscrape – A standalone and scriptable web scraper in Go"

sunshadow — Sat, 11 Nov 2023 17:41:39 +0000

Crul looks nice, though, you cannot imagine how many startups that I've seen failed doing a very similar thing as Crul. Wouldn't rely on it. The problem is complex: Humans generating messy pages

New comment by sunshadow in "Show HN: Flyscrape – A standalone and scriptable web scraper in Go"

sunshadow — Sat, 11 Nov 2023 17:35:52 +0000

You don't use XPath&CSS selectors at all (Except if you dont have choice). You rely on more generic stuff, e.g, "the button that has 'Sign in' on it":

    await page.getByRole('button', { name: 'Sign in' }).click();

See playwright locators: https://playwright.dev/docs/locators

New comment by sunshadow in "Show HN: Flyscrape – A standalone and scriptable web scraper in Go"

sunshadow — Sat, 11 Nov 2023 16:58:59 +0000

These days, I'm not even using Go for scraping that much, as the webpage changes makes me crazy and JS code evaluation is a lifesaver, so I moved to Typescript+Playwright. (Crawlee framework is cool, while not strictly necessary).

Its been 8+ years since i started scraping. I even wrote a popular Go web scraping framework previously: (https://github.com/geziyor/geziyor).

My favorite stack as of 2023: TypeScript+Playwright+Crawlee(Optional) If you're serious in scraping, you should learn javascript, thus, playwright should be good.

Note: There are niche cases where lower-level language would be required (C++, Go etc), but probably only <%5

New comment by sunshadow in "Show HN: Cost&Time AI Estimator for MVP and Full Product. Seeking Your Feedback"

sunshadow — Fri, 10 Nov 2023 06:01:19 +0000

It would be nice to see it open source. As im concerned about the privacy policy as its a really valuable information

New comment by sunshadow in "Sharing Screen with GPT 4 vision"

sunshadow — Thu, 09 Nov 2023 13:17:08 +0000

Give it 1 year

New comment by sunshadow in "Using GPT-4 Vision with Vimium to browse the web"

sunshadow — Thu, 09 Nov 2023 11:10:56 +0000

But its too expensive to become practical with the OpenAI API. Also, demo is cool until you see the real-world webpages, then you'll realize that this only works less than %50 of webpages.

New comment by sunshadow in "Using GPT-4 Vision with Vimium to browse the web"

sunshadow — Thu, 09 Nov 2023 10:48:23 +0000

You're good until this is cheaper than your salary.

New comment by sunshadow in "Automated, black-box method for jailbreaking GPT-4, Claude-2, Llama"

sunshadow — Tue, 07 Nov 2023 22:26:01 +0000

I don't understand why people still spend time on jailbreaks of the proprietary models, while they can easily use uncensored open-source models these days. I feel like its kind of waste of time.

New comment by sunshadow in "Show HN: ChatGPT vs. Jurassic vs. Bard vs. Claude"

sunshadow — Sat, 07 Oct 2023 09:31:46 +0000

Unfortunately its gonna be abused like hell so you'll end up shutting it down or requiring API keys for each one of them :(