After using the SOG PowerPint for over a year and the Leatherman Skeletool CX for a month, I feel ready to share my thoughts and ultimately choose which tool I choose for my every day carry (EDC).
Read More
The Holy Land, centered around Jerusalem, is the region in the Middle East which is considered sacred by Judaism, Christianity, and Islam due to its significance in their respective religious histories and scriptures. It has changed hands between different ethnic groups and empires. It has seen never-ending strife. When peace comes to this land is probably when peace comes to this world.
Read More
AI image generators have become extremely popular since Midjourney burst onto the scene. Since then, many other AI generators have emerged, but Midjourney remains somewhat inaccessible, and others come with strict limitations. However, I heard that Grok offers image generation with generous limits, so I decided to give it a try.
Read More
Retrieval Augmented Generation or RAG is a technique that enables generative artificial intelligence (Gen AI) models to retrieve and incorporate new information. It modifies interactions with a large language model (LLM) so that the model responds to user queries with reference to a specified set of documents, using this information to supplement information from its pre-existing training data. This allows LLMs to use domain-specific and/or updated information (Wikipedia) . It is another fundamental LLM customization technique that is relatively simple, low-cost, and still requires no model modifications.
Read More
Prompt Engineering or Prompting is the process of structuring or crafting an instruction in order to produce the best possible output from a generative artificial intelligence (AI) model (Wikipedia). It is the most fundamental LLM customization technique and is simple, low-cost, and requires no model modifications.
In this post, we will explore some common prompting techniques such as:
- Zero-Shot Prompting – Asking the LLM to answer without prior examples.
- Few-Shot Prompting – Providing a few examples in the prompt to improve accuracy.
- Chain-of-Thought (CoT) Prompting – Encouraging step-by-step reasoning to enhance complex problem-solving.
- Meta Prompting – Guide the reasoning process by introducing structure, constraints, or multi-step instructions.
- Self-Consistency Prompting – Generate multiple solutions and select the most frequently appearing answer.
- Tree of Thought (ToT) Prompting – Exploring multiple reasoning paths before selecting an answer.
- Prompt Chaining – Not exactly a prompting technique, it is using the output of the previous prompt as input to the next prompt.