I'm Yotam, a digital tinker from Tel Aviv. My interests include language models (LLMs), artificial intelligence (AI), web development, web design, and entrepreneurship. I am interested in the intersection of these domains, utilising my skills to contribute to the groundbreaking technological landscape.
Currently, I focus on exploring the future of knowledge representation through the lens of LLMs. I am deeply fascinated by the potential of LLMs to revolutionise how we comprehend, analyse, and visualise data with emphasis on knowledge discovery. My work aims at prototyping intuitive and user-friendly interfaces that leverage these state-of-the-art AI models.
My primary target users are students and thinkers who consistently strive to acquire and comprehend new factual textual knowledge. Through these interfaces, I aim to enhance their reading and learning experience.
In my entrepreneurial journey, I've previously co-founded Sandbook, a social reading app for philosophy students. I currently building HypeRead AI, an experimental system that utilises AI to uncover and present knowledge hidden within the vast world of nonfiction books.
Through this platform, I aspire to make learning more engaging and accessible and to provide readers with an enhanced and comprehensive understanding of their desired topics.
Expanding on the principles of semantic similarity, I've also gained experience in semantic search. Instead of relying on traditional keyword-based searching methods, semantic search allows us to find more accurate and contextually relevant results by understanding the searcher's intent and the contextual meaning of terms within the query.
To gather and clean data, I've delved into the areas of web scraping and text cleaning. I've used Python-based tools to efficiently extract unstructured data from various online sources, then performed text cleaning to remove irrelevant information and ensure the data is suitable for downstream tasks.
I've worked with prompt engineering in LLMs to refine the experiences and to guide the model to receive data and produce accurate outputs.
In terms of tools and platforms, I've utilised the Jupyter notebook for researching the various tools and capabilities for state of the art models. I've experimented with the open-source framework Haystack for end-to-end QA systems. With Haystack, I've been able to apply fine-tuned models to extensive databases, achieving reliable results in information retrieval.
This comprehensive skill set has given me a multi-faceted perspective on AI and NLP, allowing me to tackle complex problems and build solutions that truly understand and respond to user needs. I look forward to leveraging these skills and experiences in future projects to continue pushing the boundaries of what's possible in this exciting field.
With an intermediate level of experience, I've had the opportunity to dive into both the front-end and back-end aspects of web development, including a hands-on understanding of DevOps.
My front-end experience is well-rounded with considerable knowledge in both Angular and React. I've built dynamic and responsive user interfaces using HTML integrated with Angular, appreciating the framework's powerful capabilities for single-page applications. In addition to Angular, I've utilized React for its flexibility and efficiency, building reusable components that provide a seamless user experience.
On the back-end side, my skills extend to the use of Django, a high-level Python Web framework that encourages rapid development and clean, pragmatic design. My familiarity with Python aids in crafting efficient, secure, and scalable server-side logic, further bolstering the performance of the applications I develop.
To bridge the gap between development and operations, I've ventured into the realm of DevOps. My experience includes managing AWS resources like EC2 for computing capabilities, Lambda for serverless architectures, and S3 Buckets for scalable storage. These tools have allowed me to maintain an efficient pipeline, automate repetitive tasks, reduce system discrepancies, and ensure the scalable and reliable deployment of web applications.
Through this balanced skill set, I'm able to take a holistic approach to web development, managing the lifecycle of an application from initial design and development through to deployment and maintenance. This intermediate experience in diverse aspects of web development equips me to tackle complex problems, and build intuitive, efficient, and scalable solutions.
For me, Web Design is first of all a thinking tool. A Clear Design is the first visual validation one can do with any digital product. Working as an html developer, I became more interested in design. After a year of training, Starting on my own project, I've designed my social reading app, from idea to production. After taking part in other digital projects, I started focusing on testing new ideas for interfaces with NLP (Natural Language processing ) and Machine Learning for textual knowledge.
My design style is functional and independent. I believe that good design can be purified to minimal, where never save on data flowing with accurate copy text involved.