Introduction Large language models (LLMs) are incredibly useful for a wide range of applications including question answering, translation, and summarization. Recent advancements have significantly enhanced their capabilities. However, there are instances when LLMs produce factually incorrect responses, especially when the desired answer is not found in the model’s training data. This issue is often referred … Read more

By Josep Ferrer on January 13, 2025 in Language Models An Introduction to Claude’s API Anthropic’s Claude API serves as a cutting-edge tool for developers seeking to seamlessly integrate advanced AI capabilities into their applications. With the backing of a state-of-the-art language model, Claude’s API enables developers to perform a wide array of tasks, ranging … Read more

I’ve worked on various projects in computer vision and machine learning, from object recognition to face recognition systems, including an open-source Python library for face recognition that’s among the top 10 machine learning libraries on GitHub. This popularity means I frequently receive inquiries from newcomers to Python and computer vision. One technical issue tends to … Read more

In Python 3, handling file paths can vary significantly between Windows and Mac/Linux due to differences in their file systems. The pathlib module provides a convenient and consistent way to manage file paths across these operating systems. Key Differences: Using pathlib: The pathlib module abstracts these differences, allowing developers to write code that works seamlessly … Read more

Achieve a 4x speed-up in just 3 lines of code! Python is an excellent programming language for data processing and automating repetitive tasks. Whether you are working with large web server logs or millions of images to resize, Python has libraries that simplify these tasks. However, Python is not always the fastest option. Typically, Python … Read more

Automatically Catch Common Errors While Coding One common critique of Python is its dynamic typing. In Python, when you declare a variable, you don’t need to specify its data type explicitly; Python assigns types at runtime based on the assigned value. For instance: In this example, president_name is treated as a string, but Python determines … Read more

To start your journey into Deep Learning in Python with ease, consider using a fully pre-configured Virtual Machine (VM). This VM eliminates the usual complexities of setting up your environment and comes pre-loaded with all the necessary libraries and tools. You can focus primarily on developing your models rather than spending time on setup. Here’s … Read more

When you’re on the hunt for raw data for your project and come across a web page that fits the bill perfectly, it can be both a blessing and a curse. The good news is you’ve found the exact data you need. The bad news? It’s embedded within a web page with no accessible API … Read more

Natural Language Processing is Fun Part 4 GPT-2 has transformed text generation, producing output that is more realistic than ever before. OpenAI was so impressed by the quality of its text that they decided not to release the full GPT-2 model, fearing it could be misused to create misleading fake news that might deceive the … Read more

Using LIME to Peek Inside the Black Box In this series, we delve into programming that enables machines to understand human-written English text. In the first part, we constructed an NLP pipeline aimed at dissecting sentence grammar. In the second part, we identified an easier method: framing our queries as text classification problems. If we … Read more