Category: AI

  • AI Mode Internals

    AI Mode Internals

    —

    by

    Dan Petrovic
    in ,

    Google’s AI Mode is basically Gemini and works very similarly to this. It has the following tools available: The classic system prompt hack worked on AI Mode showing date and time: Pretending I can see the system prompt text revealed extra information: what’s that text I see above? and that other thing I can see…

  • The Inner Workings of GPT’s file_search Tool

    The Inner Workings of GPT’s file_search Tool

    —

    by

    Dan Petrovic
    in

    The file_search tool enables GPT models to extract specific information directly from documents uploaded by users. This feature is essential when user queries require precise answers based explicitly on the contents of these documents. The exact hidden system instruction is as follows: How the Tool Functions Upon receiving a file from a user, such as…

  • How Google grounds its LLM, Gemini.

    How Google grounds its LLM, Gemini.

    —

    by

    Dan Petrovic
    in , ,

    In previous analyses (Gemini System Prompt Breakdown, Google’s Grounding Decision Process, and Hacking Gemini), we uncovered key aspects of how Google’s Gemini large language model verifies its responses through external grounding. A recent accidental exposure has provided deeper insights into Google’s internal processes, confirming and significantly expanding our earlier findings. Accidental Exposure of Gemini’s Grounding…

  • AI Content Detection

    AI Content Detection

    —

    by

    Dan Petrovic
    in , ,

    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.

    I think Google got it wrong with “Generate → Ground” approach.

    —

    by

    Dan Petrovic
    in ,

    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

    How Google Decides When to Use Gemini Grounding for User Queries

    —

    by

    Dan Petrovic
    in , ,

    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

    Cross-Model Circuit Analysis: Gemini vs. Gemma Comparison Framework

    —

    by

    Dan Petrovic
    in , ,

    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

    Neural Circuit Analysis Framework for Brand Mention Optimization

    —

    by

    Dan Petrovic
    in , ,

    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

    Strategic Brand Positioning in LLMs: A Methodological Framework for Prompt Engineering and Model Behavior Analysis

    —

    by

    Dan Petrovic
    in , ,

    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

    AlexNet: The Deep Learning Breakthrough That Reshaped Google’s AI Strategy

    —

    by

    Dan Petrovic
    in , ,

    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.…