Recent content on Run the Data
Six months is an eternity in the age of LLMs. In hindsight, committing to a post about how I don’t use LLMs was a bit naïve given the steady pace of LLM improvements from frontier labs. Since part two of this series, we’ve seen the release of, among others, Claude Opus 4.5, 4.6, and 4.7; GPT 5.2, 5.3, 5.4, and 5.5; Gemini Pro 3 and 3.1; Qwen 3 Max and 3.5; Kimi K2.5 and K2.6; GLM 5 and…
Most developers spend their first wishes on the obvious: fancy auto-complete, quick bug fixes, simple Q&A, and instant feedback . They fill immediate needs and provide quick bursts of productivity. But when the dust settles, these types of improvements don’t fundamentally change the developer. True transformation requires a more deliberate engagement with the tools. Forging a deeper…
Previously , I’ve written that Schrödinger’s LLMs are both overly impressive and underwhelming. This three-part series cuts through the noise to separate what’s genuinely valuable from what’s mostly just hype. In the first post, I share four practical, low-risk ways I incorporate LLMs into my daily routine while pointing out their limitations. Accelerating With Code…
In the past few months we’ve seen an incredible explosion in the capabilities of LLMs, but where are we on the S-curve? From flagship upgrades ( Claude 3.7 Sonnet , GPT 4.1 / o3 , Gemini 2.5 Pro ), to larger context windows, to the proliferation of Model Context Protocols ( MCP ) and agentic workflows , it’s safe to say the way we interact with LLMs has fundamentally changed. And yet…
Everyone gets stuck. Whether it’s technical work, drudgery, or anything in between, tasks that stop you in your tracks can be frustrating and stressful. The effects can compound when it involves your superpower and expectations are high. While there’s no panacea, I’ve collected a few tricks to help me get back on track when I hit a wall. Diagnose My first trick is to ask why ? Am…
What is a Superpower? A superpower is a skill where your relative ability is higher than your peers . That’s it. Whether you’re looking for a new job or working towards a promotion, it can be daunting to find a way to stand out in a sea of extremely capable counterparts. As a data professional, you’re going to be surrounded by technical peers. At first glance, your colleagues may…
In 2021, a series of surgeries interrupted my running for 18 months. Besides the accompanying physical and mental difficulties, I faced a reckoning with the sport itself and my relationship with it. To navigate the recovery process, I pieced together lessons I had learned along the way to create sustainable habits. I came out the other side a stronger runner with a better appreciation for…
Welcome to Run the Data ! It’s a blog about data, machine learning, and running. Author I’m Ryne Carbone, a Machine Learning Engineer and avid runner in NYC. I have a PhD in Physics and worked at the Large Hadron Collider in Switzerland before leaving academia. Since then, I’ve been largely working in Fintech. I’ve worked on a wide range of ML applications from Growth to…