Blogs

Uncovering AI's Mental Model

Posted on April 4, 2025

Click to enlarge × A few weeks ago I wrote about how Anthropic uncovered where different ideas, and facts are stored inside a large language model. Well, last week they released the results of a follow up research where they show how an AI actually reasons and evidence that rather just writing text one token at a time, the AI actually plans ahead. A few highlights from their research:

Uncovering AI's Mental Model
Posted on April 4, 2025
Click to enlarge × A few weeks ago I wrote about how Anthropic uncovered where different ideas, and facts are stored inside a large language model. Well, last week they released the results of a follow up research where they show how an AI actually reasons and evidence that rather just writing text one token at a time, the AI actually plans ahead. A few highlights from their research:

Read more
Is hype all you need in AI Research?
Posted on January 26, 2025
The last decade saw a few AI scientific breakthroughs that enabled the whole AI development to boom. For example, realizing that AI thrives on large amounts of data and GPUs. Large language models had the problem for a long time that they were difficult to train, because (1) they couldn’t be trained properly on GPUs, and they suffered from something called catastrophic forgetting. But then in 2017, the Attention is All you Need solved these two problems and within a few years we saw the development of ChatGPT and similar large language models.

Read more
5 AI Real-World Projects To Set Foot in The Door
Posted on July 31, 2024
Don’t just learn Data Science — do it! The best way to do Data science is to build real-world projects that spark your passion and resonate with you. No matter where you are in your Data science journey, you can always roll up your sleeves, get your hands dirty and experiment with things. This helps you connect the dots and challenge your understanding. Click to enlarge × If you are new to the world of AI and LLMs and want to get your feet to the door, I think the following real-world projects (in order of complexity) are good gateways into the field.

Read more
Display highlighted PDFs in Streamlit
Posted on July 30, 2024
and make LLMs more trust-worthy. Click to enlarge × Hallucination which happens when an AI model makes stuff up is a heavily discussed topic. I think this is the #1 roadblock for companies to adopt LLMs in production since people can’t 100% trust the model output. Click to enlarge Over the last years working with LLMs projects, I have realized that users greatly value the ability to retrieve the exact excerpts, sentences, or paragraphs from documents that the language models use to generate their answers.

Read more
Where is AI headed? It is about agents.
Posted on June 17, 2024
“AI agent workflows will drive massive AI progress this year” — Andrew Ng I recently watched Andrew Ng’s talk on AI agents, or what he calls agentic systems. Inspired by his insights, I would like to delve into understanding AI agents better. In this article, we will learn what agentic systems are and how to build a simple agentic system from scratch. Click to enlarge × What is an Agentic Workflow and why is it better?

Read more
Getting structured information out of images
Posted on May 21, 2024
Using the latest and most advanced OpenAI’s model called GPT-4o Click to enlarge × OpenAI recently releases GPT-4o — which is claim to be the best OpenAI’s AI model at half price (as compared to GPT4)! This new model offers real-time multimodal capabilities in text, vision, and audio with same level of intelligence as GPT4turbo but is much more efficient. This means that it has lower latency, it generates text 2x faster and very importantly, is half the price of GPT4Turbo.

Read more
Working with PDFs: The best tools for extracting text, tables and images
Posted on April 30, 2024
Lots of information comes from text data, for example in PDF documents. Handling PDFs can be particularly challenging, especially with tables and images. Click to enlarge × If you work with single modality language model, then you probably already know that it doesn’t have the ability to directly interpret or “read” documents. It is only capable of handling one type of input, such as text-only or image-only. If you need to analyse images or infographics from PDFs, for downstream tasks e.

Read more
LLM Output — Evaluating, debugging and interpreting.
Posted on December 29, 2023
Evaluating the output of GenAI models is as crucial as it is challenging. Back in the day before the GenAI time, you simply split your data into training/test/validation sets — train your model on the training set and evaluate performance on the validation and test set. In supervised learning, we use R-squared, Precision, recall, or F-sore to evaluate performance. How is a LLM evaluated? What is the ground truth when it comes to generating new texts?

Read more
Do You Understand Me? Human and Machine Intelligence
Posted on December 9, 2023
By Lan Chu and Robert Jan Sokolewicz. Click to enlarge × Terminologies In this article, we try to explore the notion of intelligence and what it means for computer programs to be intelligent. We will be dancing between different terminologies and concepts often discussed in the context of human cognition such as Understanding, awareness, intelligence, and consciousness. Even though the meaning of these terms is somewhat mysterious, we try to refer to them based on the normal usages:

Read more
GenAI’s products: Move fast and fail
Posted on December 3, 2023
Click to enlarge × In Autumn 2022, I was working on a cool project. Yes, you guessed it — finetuning a pre-trained LLM (Bert) using company-specific data. However, soon enough, ChatGPT was released and has taken the world by storm. And what is the point of me trying to finetune a LLM when there is one out there that is super powerful? I have been a huge fan of Bert so when ChatGPT was released, I got caught up in that buzz too.

Read more

Join Our Newsletter

If you want to be notified of updates on data and AI news and more, sign up for our newsletter!

Join Our Newsletter

Subscribe