Category: AI
-
AI Content Detection
As models advance, AI content detection tools are struggling to keep up. Text generated by the latest Gemini, GPT and Claude models is fooling even the best of them. We’ve decided to bring AI content detection back in-house in order to keep up. Each time a new model comes out the classifier needs a fine-tune…
-
I think Google got it wrong with “Generate → Ground” approach.
Grounding Should Come Before Generation Google’s RARR (Retrofit Attribution using Research and Revision) is a clever but fragile Band‑Aid for LLM hallucinations. Today I want to zoom out and contrast that generate → ground philosophy with a retrieval‑first alternative that’s already proving more robust in production. Quick Recap: What RARR Tries to Do Great for retro‑fitting citations onto an existing model;…
-
How Google Decides When to Use Gemini Grounding for User Queries
Google’s Gemini models are designed to provide users with accurate, timely, and trustworthy responses. A key innovation in this process is grounding, the ability to enhance model responses by anchoring them to up-to-date information from Google Search. However, not every query benefits from grounding, and Google has implemented a smart mechanism to decide when to…
-
Cross-Model Circuit Analysis: Gemini vs. Gemma Comparison Framework
1. Introduction Understanding the similarities and differences in how different large language models represent and prioritize brand information can provide crucial insights for developing robust, transferable brand positioning strategies. This framework outlines a systematic approach for comparative circuit analysis between Google’s Gemini and Gemma model families, with the goal of identifying universal brand-relevant circuits and…
-
Neural Circuit Analysis Framework for Brand Mention Optimization
Leveraging Open-Weight Models for Mechanistic Brand Positioning 1. Introduction While our previous methodology treated language models as black boxes, open-weight models like Gemma 3 Instruct provide unprecedented opportunities for direct observation and manipulation of internal model mechanics. This framework extends our previous methodology by incorporating direct neural circuit analysis, allowing for precise identification and targeting…
-
Strategic Brand Positioning in LLMs: A Methodological Framework for Prompt Engineering and Model Behavior Analysis
Abstract This paper presents a novel methodological framework for systematically analyzing and optimizing the conditions under which large language models (LLMs) generate favorable brand mentions. By employing a structured probing technique that examines prompt variations, completion thresholds, and linguistic pivot points, this research establishes a replicable process for identifying high-confidence prompting patterns. The methodology enables…
-
AlexNet: The Deep Learning Breakthrough That Reshaped Google’s AI Strategy
When Google, in collaboration with the Computer History Museum, open-sourced the original AlexNet source code, it marked a significant moment in the history of artificial intelligence. AlexNet was more than just an academic breakthrough; it was the tipping point that launched deep learning into mainstream AI research and reshaped the future of companies like Google.…
-
Revealed: The exact search result data sent to Google’s AI.
UPDATE: Addressing guardrails, hallucinations and context size. 1. People are reporting difficulties in recreating the output due to guardrails and hallucinations. 2. Snippet context sometimes grows to several chunks. Guardrails Google attempts (and in many cases) succeeds at blocking these requests, but it does so in a very clumsy way so that we actually get…
-
Beyond Rank Tracking: Analyzing Brand Perceptions Through Language Model Association Networks
This post is based on the codebase and specifications for AI Rank, an AI visibility and rank tracking framework developed by DEJAN AI team: https://airank.dejan.ai/ Abstract: Traditional SEO has long relied on rank tracking as a primary metric of online visibility. However, modern search engines, increasingly driven by large language models (LLMs), are evolving beyond…
-
Introducing VecZip: Embedding Compression Algorithm
Embeddings are vital for representing complex data in machine learning, enabling models to perform tasks such as natural language understanding and image recognition. However, these embeddings can be massive in size, creating challenges for storage, processing, and transmission. At DEJAN AI, we’ve developed VecZip, a novel approach to address this issue, and reduce the file size…