In this week’s blog, we dive into a variety of intriguing topics: building a GPT Tokenizer, the whimsy of LED Matrix Earrings, understanding Bloom Filters, and embracing simple architectures. We also explore the complexities of web scraping in Python, adapt to changes AI brings to business models, prepare for the cookie-less future with Google’s webinars, and examine the need for journalistic leaders to master business skills. Plus, we discuss how electronic music affects our brain and contemplate the Law of Shitty Clickthroughs. Join us for a journey through technology, business, and the power of music!

• Let’s build the GPT Tokenizer: The Tokenizer is a necessary and pervasive component of Large Language Models (LLMs), where it translates between strings and tokens (text chunks). Tokenizer…
• LED Matrix Earrings:
• Bloom Filters: A visual, interactive guide to what bloom filters are, when you would use them, and how they work.
• In defense of simple architectures:
• Web Scraping in Python – The Complete Guide: Build robust web crawlers using libraries like BeautifulSoup. Overcome scraping challenges and learn best practices for large scale scraping.
• Ross Sleight on AI: Adapt now, as business models are under threat: “We always overestimate the short-term and underestimate the long-term impact of things. That’s exactly what’s happening with AI today. So, in the long
• Google launches webinars to prepare publishers for the crumbling of third-party cookies: As Google moves ahead with plans to turn off third-party cookies for all Chrome users by the second part of 2024, the tech giant has announced it will hold free webinars to help publishers prepare for the phase out.
• The New Head Honcho: Journalistic Leaders Must Know How To Run A Business: Does an editor in chief exist who has not been called on to sit in an endless budget meeting or engage in some other way with the business side?

  That’s the least of it. Now more than ever, journalism needs leaders who know how to run a business, judging by an essay in Nieman Reports.

• Electronic music appears to alter our state of consciousness: Listening to electronic music makes neurons in our brain fire in time with the beat, which appears to alter our reaction time and sense of unity
• The Law of Shitty Clickthroughs: Sometimes I get asked “have you ever seen someone do XYZ to acquire customers?” Turns out, the highest vote of confidence I can give is, “No I haven’t, and that’s good – that means there’s a higher chance of it working. You should try it.”