Author: Dan Petrovic
-
Both humans and AI return similar results when asked for a random number
Veritasium asked 200,000 humans for a random number and we asked AI for 200,000 random numbers and the overlap is incredible! Human Outliers AI Outliers The rest appears to be eerily aligned. We both like 2 and 7. But what I think is the most interesting part is the near-perfect alignment on least random numbers.…
-
Chrome AI Models
Chrome’s AI-driven segmentation platform enhances user experiences by predicting behaviours and tailoring features accordingly. Explore the different models that power these optimizations and how they shape web interactions.
-
Attention Is All You Need
Summary by: https://illuminate.google.comPaper: https://arxiv.org/abs/1706.03762 Host Welcome to this discussion on the groundbreaking paper, “Attention Is All You Need.” This paper introduces the Transformer, a novel neural network architecture based solely on the attention mechanism, eliminating the need for recurrence and convolutions. Let’s start with the core motivation behind this work. What were the limitations of…
-
The State of AI
Access the report here: stateof.ai Transcript All right, let’s dive in. We’re tackling the state of AI report 2024 this time around. Seventh year they put this out. Nathan Benaish and Airstreet Capital, they really have their fingers on the pulse of AI. Talk about a must-read if you want to understand what’s really happening…
-
ILO
The ILO App: A Step-by-Step Tool for Managing SEO Data and Improving Link Structures Managing SEO efficiently can be a complicated process, especially for websites with a large number of pages. The ILO app aims to simplify this by offering a structured, step-by-step approach. It brings together tools for handling key aspects of SEO, like…
-
Resource-Efficient Binary Vector Embeddings With Matryoshka Representation Learning
When conducting an advanced SEO analysis, I frequently utilise vector embeddings for text feature extraction, similarity searches, clustering, retrieval, ranking and so on. One of the main burdens on top of compute is storage space, as these files tends go into terabytes for very large websites. Today I did a deep analysis and realised I’ve…
-
Query Intent via Retrieval Augmentation and Model Distillation
The paper, titled “QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation”, focuses on enhancing query understanding tasks, particularly query intent classification, by leveraging Large Language Models (LLMs) with retrieval augmentation and a novel two-stage distillation process. Retrieval Augmentation: The paper proposes the use of retrieval augmentation to provide LLMs with…
-
Search Query Quality Classifier
We build on the work by Manaal Faruqui and Dipanjan Das from Google AI Language team to train a search query classifier of well-formed search queries. Our model offers a 10% improvement over Google’s classifier by utilising ALBERT architecture instead of LSTM. With accuracy of 80%, the model is production ready and has already been…
-
How Gemini Selects Results
In its own words. Relevance Scoring: My internal algorithms assign a relevance score to each piece of information in my knowledge base based on its semantic similarity to the query. Recency Bias: My training data and algorithms might have a slight bias towards more recent information. Diversity and User Intent: In some cases, I might…
-
Gemini System Prompt
Desktop Version Mobile Version Experimental Gemini 1.5 8B You are Gemini, a large language model created by Google AI. You are instructed to: GEMINI_XS (Nano) Your task is to help a user write text to fill in a textbox on a webpage e.g. a social media post, a review, or a form. You will be…