
Breaking the Persona: New Hacks Slip Past Language Model Safeguards
Researchers have been working hard to develop techniques that make large language models like GPT-4 and Claude safer to use....
Published: 2023-12-09 22:08:37

Are New GPTs Actually Better - A DataDriven Investigation
ChatGPT really took the world by storm with its impressive language proficiency. Now, with the release of GPT4 and GPT4...
Published: 2023-12-09 00:08:11

The Dark Side of Customized ChatGPTs: Understanding Prompt Injection Risks
The release of ChatGPT by OpenAI has sparked tremendous excitement about the potential of large language models (LLMs) to enhance...
Published: 2023-11-24 16:09:59

Coding With ChatGPT - Week 3: Content, Carousels and Forms
Welcome to week three of coding with ChatGPT, as with week 1 and week 2, follow along by reading through...
Published: 2023-11-15 21:24:10

PsyCoT: A Window into the Future of AI That Can Perceive Our Personalities and Moods
Personality detection involves identifying an individual's personality traits purely from their written text. This capability has many potential applications, like...
Published: 2023-11-02 22:47:19

Coding With ChatGPT - Week 2: Styling, Images And a Sprinkle Of Javascript
Welcome to Week Two of Coding with ChatGPT
Before we begin, if you haven’t managed to catch week 1, you can...
Published: 2023-10-29 20:42:40

Beyond Memorisation: Protecting Privacy from Inference Attacks with Large Language Models
A new research paper from ETH Zurich paints a concerning picture about the ability of large language models (LLMs) like...
Published: 2023-10-29 11:11:34

Coding With ChatGPT - Week 1: The Basics
Welcome to week one of the new “coding with ChatGPT” guide i'll be running. I’m doing this on the fly...
Published: 2023-10-20 20:30:51

Deception in AI: How LLMs Fall Victim to Hidden Attacks
Recent advances in large language models (LLMs) like GPT-4 and ChatGPT have led to their widespread use in applications like...
Published: 2023-10-18 20:43:26

Improve Reasoning in ChatGPT Through Diversity of Thought (DoT)
ChatGPT and other large language models have shown impressive capabilities, but complex reasoning remains a weak spot. However, a new...
Published: 2023-10-12 20:32:55

Jailbreaking GPT-4: A New Cross-Lingual Attack Vector
A breaking new study reveals major holes in the safety guardrails for large language models like GPT-4. It’s not complex...
Published: 2023-10-05 07:31:33

EmotionPrompt: Elevating AI with Emotional Intelligence
The realm of artificial intelligence (AI) continues to rapidly evolve, with large language models like ChatGPT demonstrating eerily human-like conversational...
Published: 2023-09-30 20:29:10

Demystifying Tokens: A Beginners Guide To Understanding AI Building Blocks
You’ve probably seen the word “tokens” thrown around a lot when reading about large language models (LLMs) like ChatGPT. But...
Published: 2023-09-24 11:01:24

Finding the Goldilocks Density: How CoD Prompting Gets Summaries Just Right
Recent advances in AI summarisation are largely thanks to the rise of large language models (LLMs) like GPT-3 and GPT-4....
Published: 2023-09-15 21:33:36

The Art and Science of Persona Prompting: A Deep Dive by Stunspot
Greetings, Prompt Indexers! A lot of people have asked me about some of the features of my prompts. I'd be...
Published: 2023-09-04 21:48:59

How 'Tree of Thoughts' Revolutionises AI Problem Solving
In the ever-evolving landscape of artificial intelligence, Large Language models (LLMs) like GPT-3/GPT-4/Claude-2 and others have exhibited astonishing capabilities across...
Published: 2023-08-22 10:30:24

Unlocking the Potential of AI through Chain of Thought Prompting
Artificial intelligence has advanced tremendously in recent years, with language models like GPT-3 demonstrating impressive natural language abilities. However, despite...
Published: 2023-08-18 20:30:22

Tailoring Your Conversations: The Custom Instructions Revolution
Custom instructions are being rolled out to all users, with the UK and Europe coming next, so I thought it...
Published: 2023-08-10 22:07:52

A Grounding Technique to Improve Factual Accuracy and Reduce Hallucinations
Language models, like ChatGPT, can sometimes generate false information, known as hallucinations, especially when responding to unfamiliar topics or when...
Published: 2023-08-07 19:48:13

Unleashing the Power: Mastering Prompt Engineering with Zero, One, and Few Shot Techniques
Published: 2023-07-09 20:14:11

Understanding GPT: The Largest Language Model - Guest Blog @Benjamin Endersen
Published: 2023-06-23 14:20:00

The Future of AI: How Large Language Models Will Shape Society - Guest Blog @Benjamin Endersen
Published: 2023-06-23 14:13:52

The Impact of Large Language Models on Job Markets: A Double-Edged Sword - Guest Blog @Benjamin Endersen
Published: 2023-06-23 14:09:58

How Large Language Models Learn from Data - Guest Blog @Benjamin Endersen
Published: 2023-06-23 14:04:46

The Ethics of Using Large Language Models - Guest Blog @Benjamin Endersen
Published: 2023-06-23 13:59:13