Untitled image


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…
AJH: I generated this via the ChatGPT Deep Research tool. Currently, a ChatGPT Plus user ($20/month) can run ten ‘Deep Research’ tasks a month. I’ll conduct deep research into the current parallels between the U.S. (last 10 years) and pre-WWII Germany, analyzing political, economic, social, and media-related factors. The research will incorporate: I’ll gather the…
If your goal is to extract everything possible from documents – text, metadata, layout, embedded objects, and even inferred insights using AI – then a simple PDF-to-text tool won’t cut it. You need a multi-pass, layered pipeline that combines traditional parsers with advanced AI models. This document outlines the most capable open-source tools available today,…
I’ve been testing the GPT Researcher tool; I used it to review what the impact might be of a two month internet outage in North America.
Calculating the Digits of Pi: Benchmarking the Bailey–Borwein–Plouffe (BBP) formula and the Chudnovsky algorithm Don’t judge me; what do you do on a Wednesday night? I asked ChatGPT to spit out some Python code to calculate pi to 1,000 digits. Then asked if it could speed it up. Computing the digits of π (pi) is…