TestDriver.ai | https://testdriver.ai | QA Engineers, Sales | Austin / Remote | Full-time / Part Time 95% of companies are still wasting time manually testing due to shortcomings in Playwright, Cypress, and other frameworks. Developers rank testing as the #1 blocker to release. We've built an AI Agent that performs manual testing on it's own VM with complete desktop access. It works like a specialized "Claude... - Source: Hacker News / 5 months ago

Kadoa | Senior Software Engineer | Remote (Europe) | Full-Time | https://kadoa.com At Kadoa, we are building the foundational infrastructure for unstructured data ETL. We enable any organization to instantly transform unstructured data (websites, documents, emails, etc.) into structured insights - without code or maintenance overhead. We are VC-funded with strong traction. There are two official roles, but we... - Source: Hacker News / 5 months ago

We've been working on AI-automated web scraping at https://kadoa.com and our early experiments were similar to yours. We started when only the expensive and slow GPT-3 was available, which pushed us to develop a cost-effective solution at scale. Here is what we ended up with: - Extraction: We use codegen models to generate CSS selectors or XPath extraction code. This is more efficient than using LLMs for every... - Source: Hacker News / 9 months ago

> Data extraction/structuring data is the only serious application of LLMs I fully agree. I realized this early on when experimenting with GPT-3 for web data extraction. We then started seeing a lot of demand for automating rule-based web scraping stacks (lots of maintenance, hard to scale), which led to the creation of our startup (https://kadoa.com). AI won't eliminate our jobs, but it will automate tedious,... - Source: Hacker News / 11 months ago

You're right, LLMs are really good at extracting and structuring data from third party sources. I've been working on a "Zapier for data extraction" for this reason: https://kadoa.com. - Source: Hacker News / almost 2 years ago

We're using LLMs to generate web scrapers and data processing steps on the fly that adapt to website changes. Using an LLM for every data extraction, as most comparable tools do, is expensive and slow, but using LLMs to generate the scraper code and subsequently adapt it to website modifications is highly efficient. Try it out https://kadoa.com. - Source: Hacker News / almost 2 years ago