In the midst of so much information—new models, post-training strategies (read: RL), and others—I found myself very excited when I first read the blog post about the RLM approach. The reason is simple: inference strategies are mostly overlooked and non-sexy in terms of discussion, yet very present in AI engineering day-to-day (Chain of Thought, ReAct, etc.).…
Continue reading →Probably like a lot of you, I’ve been having a blast using Cursor (or any other AI development workflow). It feels like the future, having complete snippets of code that can go from fixing issues to adding entirely new features.…
Continue reading →A lot has already been said about where and for what LLMs are good for (an honest summary I like is here) but I feel that, even though there new papers and techniques coming out every day on AI space, I haven't heard much about the art (yes, art) of making reliable products with them.…
Continue reading →Welcome to LazyHumanity, where we believe that laziness—when properly channeled—moves the world forward. Our mission is simple yet profound: to create tools that automate the mundane and amplify what makes us uniquely human. In our rapidly evolving technological landscape, we're witnessing an unprecedented opportunity.…
Continue reading →