Open post tag_based_prompting

Tag Based Prompting for Better Prompting Performance

Large Language Models (LLMs) have amazed us with their ability to generate human-quality text, translate languages, and answer complex questions. But what happens when you need them to tackle something outside their general knowledge base – like predicting the properties of a protein or translating a highly structured technical document? That's where tag-based prompting comes...

Open post empathy

ChatGPT’s artificial empathy is a language trick. Here’s how it works

Anthropomorphism occurs when we attribute human characteristics to non-human entities like animals or machines. Chatbots, such as ChatGPT, Gemini and Copilot, encourage this by imitating human language to communicate with us, going beyond using mere familiar words and phrases to adopt human patterns of communication. By doing this, they are able to hold contextualised, coherent...

Open post long context

The Long Context

In "You Exist In The Long Context," Steven Johnson explores the advancements in large language models (LLMs), particularly the significant impact of long context windows. Johnson illustrates this progress by creating an interactive game based on his book, showcasing the LLM's ability to handle complex narratives and maintain factual accuracy. He draws a parallel between...

Open post mcp

The Model Context Protocol

Anthropic's Model Context Protocol (MCP) is an open-source standard for connecting AI assistants to various data sources. MCP employs a client-server architecture, enabling two-way communication between AI applications (clients) and data providers (servers) via different transports like stdio and HTTP with SSE. The protocol facilitates access to resources, tools, and prompts, enhancing AI response relevance...

Open post Tinytroupe

TinyTroupe: Simulating Human Behaviour with AI

Microsoft has released TinyTroupe, an open-source Python library that uses large language models to simulate human behaviour in virtual environments. This allows for testing digital advertising, software, and generating synthetic data for machine learning. The library enables the simulation of multiple AI agents ("TinyPersons") with individual personalities interacting within a simulated world ("TinyWorld"), facilitating virtual...

Open post Meta Pixel

How We Built a Meta Pixel Inspector

The first large-scale, crowdsourced study that monitors how Meta tracks people across the internet By: Surya Mattu, Angie Waller, Simon Fondrie-Teitler, and Micha Gorelick Introduction Have you ever shopped for a product online only to see the item appear ad nauseam in your Facebook or Instagram feeds? This is often the result of the Meta...

Scroll to top