There’s also llm-scraper in TypeScript

https://github.com/mishushakov/llm-scraper

Something similar I worked on in the past https://github.com/lucgagan/auto-playwright/

Does it use ChatGPT every time you run the test or only when a test fails (to check if the selector has changed)?

Awesome! The problem with extracting schema automatically is that you won't know what comes out of it upfront and it could be changing on every run. What I'm trying to do is enable scraping webpages in a structured (and type-safe!) manner.

Awesome! Keep in mind there's already scrapeghost and entities-extraction-web-scraper in Python.

I've tried using it with Groq's Llama 3 70B and it worked well :)

Definitely. Smaller models like Haiku are already pretty capable (and cheap!)

How does Haiku do with instruction following?

In my experience Anthropic models are more steerable (requires less prompting) than OpenAI's. For example in code-generation, I'd tell GPT-4 to not include any comments, yet sometimes it would just ignore this. Have not experienced this with Opus yet.

Thank you! I’m working on supporting local llms via llama.cpp currently, so cost won’t be an issue anymore

Given that the ollama API is openai compatible, that should be a drop in, no?

Not really, I believe it’s missing function calling

Edit: and grammar as well

Ahh yeah gotcha

Correct. JS sites are supported out of the box since we're using Playwright!

Nice! Markdown output would be an awesome addition

use something like Browserbase?

If I have a EU permanent residency, but no citizenship yet, will I lose my residency if I decide to move to the US?

IANAL but it depends on the country, there is no such thing as EU permanent residency.

For Germany the answer is yes, but you could fake it at the risk of getting your PR revoked if they ever find out.

Same experience here. I'd say building something HN viewers find cool almost guarantees that you won't make any money with it.

successful yes, profitable no

connections, lots of

did not help with a job