fredthedeve
Show HN: Permit Watch, Turning Ireland's work permits into a job-demand proxy
I'm a Stamp 1G student in Ireland. DETE's data is gold but buried in Excels. Built this to filter/search: HSE's 12,501 health permits (2024), IT trends (6,788 issued), CSRI success odds (e.g., 88.8% for US devs at Meta Dublin).Proxy insight: High permits = hot sectors/companies for non-EU talent.100% DETE open data. Feedback?
Re:Show HN: RAGsplain – What does your RAG model see before it answers?
on Friday July 18, 2025 @12:35PM (#44606701)
Thanks a lot for the feedback! Really appreciate you trying it out. For longer videos, transcription can definitely take a bit... I'm working on moving processing to more powerful servers (currently running off my home machine)
For a quick overview on how it works and to get past those initial steps, this demo video of ragsplain might help:
Show HN: RAGsplain – What does your RAG model see before it answers?
Are your RAG models hallucinating? Maybe the issue isn't the LLM, but the retrieval phase.I built RAGsplain (ragsplain.com) to help debug this. You upload documents (PDFs, audio, YouTube links), choose a retrieval method (semantic, keyword, or hybrid), and see the exact chunks of context passed to the model — match scores included.Turns out: when retrieval is bad, even the best model can’t...