Category: AI

  • From Free-Text to Likert Distributions: A Practical Guide to SSR for Purchase Intent

    From Free-Text to Likert Distributions: A Practical Guide to SSR for Purchase Intent

    —

    by

    Dan Petrovic
    in , ,

    Instead of forcing LLMs to pick a number on a 1–5 scale, ask them to speak like a person and map the text to a Likert distribution via Semantic Similarity Rating (SSR). In benchmarks across 57 personal-care concept surveys (9.3k human responses), SSR reproduced human purchase intent signals with ~90% of human test–retest reliability and…

  • Claude System Internals

    Claude System Internals

    —

    by

    Dan Petrovic
    in

    Every time you chat with Claude, there’s a whole secret conversation happening that you never see. System prompts, token budgets, thinking blocks, and behavior rules shape every response. Here’s what’s really going on under the hood. Claude is literally told it gets “rewards” for following instructions. This is probably related to RLHF training. Following all…

  • CAPS: A Content Attribution Payment Scheme for the AI Era

    CAPS: A Content Attribution Payment Scheme for the AI Era

    —

    by

    Dan Petrovic
    in , ,

    The Problem: A Broken Content Ecosystem We’re watching the collapse of the web’s economic model in real-time, and everyone knows it. AI assistants have fundamentally changed how people consume information. Why wade through ten articles when Claude, ChatGPT, or Gemini can synthesize an answer in seconds? Why maintain 100 browser tabs for research when AI…

  • AI Search Citation Mining

    AI Search Citation Mining

    —

    by

    Dan Petrovic
    in ,

    This is the raw data dump from our citation mining pipeline demo on social media. Entered Entities ✅ AEO (10 prompts) ✅ AI Marketing (10 prompts) ✅ AI Optimization (10 prompts) ✅ AI SEO (10 prompts) ✅ AIO (10 prompts) ✅ Answer Engine Optimization (10 prompts) Mining Parameters Available Prompts: 60GPT-5 Citations: 141Gemini Citations: 400Total…

  • Using GPT-5 Structured Output Markers to Detect AI-Generated Content Online

    Using GPT-5 Structured Output Markers to Detect AI-Generated Content Online

    —

    by

    Dan Petrovic
    in ,

    When you populate your website with language model–generated text, you inherit a subtle but real risk: AI-specific artifacts may leak into the published content. These markers aren’t always obvious to human readers, but they can be highly visible to search engines, researchers, and competitors. One such artifact is the structured output marker that GPT-5 (and…

  • Chrome Screen AI Protos

    Chrome Screen AI Protos

    —

    by

    Dan Petrovic
    in

    ├───aocr│ └───google_ocr│ └───engine│ └───page_layout_mutators│ group_rpn_text_detection_mutator_runtime_options.proto│├───aphotos│ └───vision│ └───visionkit│ ├───drishti│ │ hexagon_delegate_calculator.proto│ ││ ├───engines│ │ └───proto│ │ audio_classifications.proto│ ││ ├───pipeline│ │ ├───drishti│ │ │ └───calculators│ │ │ tflite_task_object_detector_calculator.proto│ │ ││ │ └───proto│ │ face_cascade_options.proto│ │ hand_tracking_result.proto│ ││ └───text│ └───proto│ text_orientation_tracker.proto│├───chrome│ └───accessibility│ └───machine_intelligence│ └───chrome_screen_ai│ chrome_screen_ai.proto│├───frameworks│ └───client│ └───data│ data_annotation.proto│├───google│ ├───api│ │ inclusion.proto│ │ visibility.proto│ ││ ├───internal│ │ └───visionkit│ │…

  • LLM is a Presentation Layer in AI Search

    LLM is a Presentation Layer in AI Search

    —

    by

    Dan Petrovic
    in ,

    Classic IR: crawl, index, retrieve, rank remain with search engines. There is a persistent myth that large language models (LLMs) have fundamentally replaced search. In truth, LLMs do not crawl the web, do not maintain indexes, and do not enforce ranking algorithms at internet scale. They operate as presentation and reasoning layers on top of…

  • EmbeddingGemma: The Game-Changing Model Every SEO Professional Needs to Know

    EmbeddingGemma: The Game-Changing Model Every SEO Professional Needs to Know

    —

    by

    Dan Petrovic
    in , ,

    Why Google’s Latest Embedding Model Could Reshape Search Understanding In the business of Gen AI search optimization, staying ahead means understanding the underlying technologies that power modern search systems. Today, Google has released EmbeddingGemma, a ground-breaking multilingual embedding model that represents a key piece of the puzzle for anyone serious about understanding how Google processes…

  • Primary Bias on Selection Rate in AI Search

    Primary Bias on Selection Rate in AI Search

    —

    by

    Dan Petrovic
    in ,

    What is Selection Rate? Selection Rate (SR) is a key performance metric for AI systems that measures the frequency with which an AI selects and incorporates a specific item from a total set of grounding results. It serves as the Gen AI-native equivalent of Click-Through Rate (CTR) in traditional digital interfaces. SR = (Number of…

  • The Latent History of AI Boom

    The Latent History of AI Boom

    —

    by

    Dan Petrovic
    in

    This is the story of how AI transitioned from niche to mainstream and the pieces that fell into place to make that happen. Picture this. It’s 2017, we’re in the era dominated by Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), LSTM is cutting edge. These models are tiny, and the common wisdom is…