Untitled image


Interactive demos for LiteParse — a fast, local, model-free document parser. Includes a parser comparison (LiteParse vs PyPDF vs PyMuPDF), visual citation search with bounding boxes, and a Claude Code research skill.
Testing a new-to-me tool – genspark.ai – I basically asked for a report on recent discoveries in Egyptology. Link to that on their site: https://www.genspark.ai/spark/recent-breakthroughs-in-egyptology-a-comprehensive-report-april-2025/c8d23bec-5654-49e3-b43c-5985e357174b Looks like you get one free use; or at least – I used all my credits. I also included a review of the article by ChatGPT at the end. Recent…
A recent large-scale experiment rigorously compared human performance to that of AI—specifically ChatGPT-4 and Bard—in creative and strategic tasks. In open-ended creative challenges (e.g., describing future societies or inventing novel products), ChatGPT-4 consistently produced responses rated as significantly more creative than those generated by humans. Although humans using AI assistance (HumanPlusAI) improved their creative output…
Here is an AI generated podcast via https://notebooklm.google.com/ using content generated with GPT-Researcher. Audio podcast: PDF:
I’ve been using an AI powered research tool: GPT Researcher One can take the code from GitHub and run it locally. I’ve been intrigued by how fast the tool can create reasonably useful output. As a test of the tool, I asked it to research: The tool ran for a couple minutes and provided the following (PDF at…