Manipulation
LLMs are getting better at character-level text manipulation
Recently, I have been testing how well the newest generations of large language models (such as GPT-5 or Claude 4.5) handle natural language, specifically counting characters, manipulating characters in a sentences, or solving encoding and ciphers. Surprisingly, the newest models were able to solve these kinds of tasks, unlike previous generations of LLMs. Character manipulation#…
The Art of Duolingo Notifications: The Subtle Manipulation of Language Learners
Let’s get something straight: Duolingo is a brilliant app. It’s become a household name in the realm of language learning, and for good reason. The bite-sized lessons, the daily streaks, the gamified points, the whole dopamine-driven experience—it works. It works really well. And it’s not just the design that makes it addictive—it’s the notifications. Duolingo…