Hacker News: startages

New comment by startages in "Show HN: See when ChatGPT or Perplexity sends a visitor to your site"

startages — Wed, 08 Jul 2026 15:56:48 +0000

Thanks, appreciate the star. If you hit any snag deploying it, let me know. Curious what you're mainly after, the AI-referral alerts or the crawler side?

Show HN: See when ChatGPT or Perplexity sends a visitor to your site

startages — Wed, 08 Jul 2026 15:28:52 +0000

Article URL: https://github.com/surfacedby/ai-traffic-alerts-for-cloudflare

Comments URL: https://news.ycombinator.com/item?id=48833236

Points: 1

# Comments: 3

Claude Fable 5 missed a bug that Sonnet 4.6 caught

startages — Wed, 10 Jun 2026 17:51:41 +0000

Article URL: https://alikhallad.com/i-tested-claude-fable-5-against-private-benchmarks-it-has-never-seen-here-is-where-it-failed/

Comments URL: https://news.ycombinator.com/item?id=48480057

Points: 3

# Comments: 0

New comment by startages in "Stripe is friendly to “friendly fraud”"

startages — Wed, 27 May 2026 04:57:18 +0000

I help a lot of client with their ecommerce websites (mostly WooCommerce), attacks became so common recently, could be AI, but I found the best way to deal with this is to trace the patterns in access log and block the same patterns of checkout submission, this have worked really well for me. There are a lot of card testing attacks that Stripe doesn't care to handle as well as a lot of other fraud techniques, but there is always a pattern, especially automated ones. There is country, IP range, certain behavior (eg; no js, or direct api calls..etc). I really think it's easy to deal with this if you're willing to look deeper than a dashboard.

Google Search Is Becoming an AI Agent

startages — Wed, 20 May 2026 11:40:42 +0000

Article URL: https://surfacedby.com/blog/google-search-is-becoming-an-ai-agent

Comments URL: https://news.ycombinator.com/item?id=48206149

Points: 1

# Comments: 0

New comment by startages in "I don't think AI will make your processes go faster"

startages — Sun, 17 May 2026 15:54:41 +0000

Now it's worst, you get an PDF export of a long ChatGPT chat history with one sentence "Can you give an estimation for this?"

New comment by startages in "I prompted ChatGPT, Claude, Perplexity, and Gemini and watched my Nginx logs"

startages — Mon, 20 Apr 2026 17:49:57 +0000

How's this going to burn money?

New comment by startages in "I prompted ChatGPT, Claude, Perplexity, and Gemini and watched my Nginx logs"

startages — Mon, 20 Apr 2026 16:38:13 +0000

I did use AI to organize my ideas but I didn't think it was that bad, I'll modify and make it easier to read.

Anyway, in my test I saw zero requests from any Google UA after multiple Gemini and AI mode prompts that should have triggered grounding, so the working interpretation is that Gemini served from its own index/cache rather than doing a live provider-side fetch. The original phrasing was fuzzier than it should have been.

New comment by startages in "I prompted ChatGPT, Claude, Perplexity, and Gemini and watched my Nginx logs"

startages — Mon, 20 Apr 2026 16:34:05 +0000

Added $http_accept and re-ran. None of them use text/markdown. Results:

ChatGPT-User/1.0 text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,/;q=0.8,application/signed-exchange;v=b3;q=0.9 Claude-User/1.0 / Perplexity-User/1.0 (empty, no Accept header) PerplexityBot/1.0 (empty, no Accept header) ChatGPT sends a Chrome-style Accept string. Claude sends a wildcard. Perplexity sends nothing at all. Gemini didn't fetch in my test.

Also worth noting: Claude-User hit /robots.txt before the page.

I prompted ChatGPT, Claude, Perplexity, and Gemini and watched my Nginx logs

startages — Mon, 20 Apr 2026 15:22:01 +0000

Article URL: https://surfacedby.com/blog/nginx-logs-ai-traffic-vs-referral-traffic

Comments URL: https://news.ycombinator.com/item?id=47835646

Points: 135

# Comments: 23

Show HN: Search Without AI, a Chrome Extension to Clean Up Google Search

startages — Mon, 20 Apr 2026 12:15:19 +0000

Article URL: https://chromewebstore.google.com/detail/search-without-ai/lfbekhabiijoldclghpfjgbcfdnnnobk

Comments URL: https://news.ycombinator.com/item?id=47833180

Points: 1

# Comments: 0

New comment by startages in "€54k spike in 13h from unrestricted Firebase browser key accessing Gemini APIs"

startages — Thu, 16 Apr 2026 13:52:16 +0000

Yeah, that the main reason I never use services like Google Cloud if I don't have to, it's impossible to have a hard cap, and anyone pretending to be an expert, is just off. Google says that they can't provide a hard cap because that would mean shutting down all your services..bla bla, but at least give users the option.

New comment by startages in "GPT-5.4"

startages — Fri, 06 Mar 2026 07:31:43 +0000

I thought I had something wrong within my setup, I could never use Codex 5.3 while everyone else was praising it. It uses some weird terms and complex jargon and doesn't really make it clear what it was doing or planning to do unlike Opus which makes things clear, this allows me to give accurate feedback and change plans and make proper decision.

New comment by startages in "MCP server that reduces Claude Code context consumption by 98%"

startages — Sun, 01 Mar 2026 09:19:07 +0000

Not bad, but it sacrifices accuracy and there are risks of causing more hallucinations from having incomplete data or agent writing bad extraction logic. So the whole MCP assumes Claude is smart enough to write good extraction scripts AND formulate good search queries. I'm sure thing could expand in the future to something better, but information preservation is a real issue in my experience.

New comment by startages in "Gemini 3.1 Pro"

startages — Fri, 20 Feb 2026 16:09:59 +0000

This is misleading. I'm running a live experiment here: https://project80.divcrafts.com/

There are 4 models, all receiving the exact same prompts a few times a day, required to respond with a specific action.

In the first experiment I used gemini-3-pro-preview, it spent ~$18 on the same task where Opus 4.5 spent ~$4, GPT-5.1 spent ~$4.50, and Grok spent ~$7. Pro was burning through money so fast I switched to gemini-3-flash-preview, and it's still outspending every other model on identical prompts. The new experiment is showing the same pattern.

Most of the cost appears to be reasoning tokens.

The takeaway here is: Gemini spends significantly more on reasoning tokens to produce lower quality answers, while Opus thinks less and delivers better results. The per-token price being lower doesn't matter much when the model needs 4x the tokens to get there.

New comment by startages in "WordPress.org bans WP Engine"

startages — Thu, 26 Sep 2024 09:48:01 +0000

WordPress Foundation is paying for the servers, so I guess they have the right to choose who gets access or not. Using the resources as a single person or a small business is not the same as using them from a hosting company with millions of websites. Other hosting companies contribute to the foundation which keeps the service running. If WPEngine isn't contributing anything, it would be unfair for other contributors/sponsors. Especially that they are making a large amount of money from it.

New comment by startages in "Ask HN: What are you working on (August 2024)?"

startages — Sun, 25 Aug 2024 13:10:43 +0000

Working on an audio watermarking system.

I've got the API ready, which requires 2 main values: - The original file ( which can be sent as a file, or hosted internally and requested using an ID ) - The data that needs to be printed into the audio file.

The API will return a watermarked version of the audio file that you can use later to extract the same data you sent before.

It's currently being tested on a production website, will wait for feedback, improve, and create an actual service out of the API.

New comment by startages in "GitHub was down"

startages — Wed, 14 Aug 2024 23:19:21 +0000

It's 00:16, just about to go to bed, I ran `git push` and it's not working. Check Github, says it's down, I think it's only me, maybe I'm blocked, Github can't be down. Come here to check and it's down for everyone, such a relief.

New comment by startages in "Ask HN: Who wants to be hired? (August 2024)"

startages — Thu, 01 Aug 2024 23:22:05 +0000

- Location: Morocco - Remote: Yes

- Willing to relocate: Depends

- Technologies: Full-stack Web Developer (PHP, SQL, jQuery, WordPress, WooCommerce, Shopify, HTML, CSS, jQuery, Tailwind, Figma, Git..etc ) + DevOps experience ( AWS, GCP, Docker ) + A little bit of experience with Python, FastAPI.

- Résumé/CV: https://docs.google.com/document/d/1_F8snhgH0wIw6ol2dIJNQuwC...

- Email: me@alikhallad.com

Also open to one-time projects.

New comment by startages in "Ask HN: Who is hiring? (July 2024)"

startages — Tue, 02 Jul 2024 16:22:38 +0000

Hello, I've sent you an email, I'm really interested in this job. Would also love to learn Japanese as a language.