In brief (updated): We’re now at 5,001 km (about 4,977 km driven since purchase). Gas-only, we’re averaging ~1.57 L/100 km so far. If we include estimated electricity (based on the car’s reported 13.1 kWh/100 km and $0.185/kWh), our total “energy cost” works out to about $3.87 per 100 km. Compared to our old 2016 Civic…
In brief: After 3,940 km in our Toyota 2025 Prius PHEV, we’re running about $3.59 per 100km on energy (gas + electricity) compared to $11.65 per 100km (gas only) in our 2016 Honda Civic. That’s a 69% reduction in driving costs, saving approximately $318 over three months. So in our particular usage, we are covering…
I asked www.sora.com for Jurassic: 1999 and stated it was ‘sort of’ a cross-over concept and asked for an image. The ‘episode’ created below was generated using the InvokeLLM from app.base44.com. Episode Title: “Jurassic Frontier” Setting the Stage: Act 1: Discovery and Danger Act 2: Ethical Dilemmas and Survival Conclusion: Choices and Consequences I wanted…
Modern systems can query several LLMs (or one LLM with diverse prompts) and fuse their outputs into a superior answer. For example, the Conceptual Boolean Operations framework issues the same query to multiple providers, then applies Semantic XOR (and related operations) to compare responses. Conceptual XOR extracts the unique concepts each model brings (while AND…
Large-language-model (LLM) ensembles promise higher factual accuracy and richer answers than any single model, but only if the pipeline is designed to measure and mitigate bias while capturing the data needed for continuous improvement.This article describes an end-to-end pattern built around semantic XOR merging, independent judging, and rigorous logging. 1. Conceptual backdrop Element Purpose Candidate…
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,…
Earlier this month I ran a ChatGPT Research task to review the election status. I ran it again to update it; here is the output. “Great — I’ll run a deep research pass focused on the 2025 Canadian federal election, building on earlier findings to identify new inflection points, updated polling, and whether the projected…
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…
I’ve been using ChatGPT Plus’s ‘Deep Research’ tool. I asked for detail about the upcoming election. Canadian Federal Election 2025: Outlook and Analysis Likely Winner: Polling and Projections Election Date and Context: Canada’s next federal election is set for April 28, 2025, called as a snap election by newly installed Prime Minister Mark Carney (Liberal)…