February 2026

I’ve been a data engineer for years, and if there’s one thing I’ve learned, it’s this: pipelines don’t explode overnight. They rot. Slowly. One shortcut at a time, one “we’ll fix it later” at a time, until you’re staring at a 3 AM PagerDuty alert, wondering how everything got this bad. This article is the field guide I wish I’d had when I started. These are the five anti-patterns I’ve seen destroy pipeline reliability across startups and enterprises […]

Ver mais

We investigate how formal temporal logic specifications can enhance the safety and robustness of reinforcement learning (RL) control in aerospace applications. Using the open source AeroBench F-16 simulation benchmark, we train a Proximal Policy Optimization (PPO) agent to regulate engine throttle and track commanded airspeed. The control objective is encoded as a Signal Temporal Logic (STL) requirement to maintain airspeed within a prescribed band during the final seconds of each maneuver. To enforce this specification at run time, […]

Ver mais

Coalition formation concerns strategic collaborations of selfish agents that form coalitions based on their preferences. It is often assumed that coalitions are disjoint and preferences are fully known, which may not hold in practice. In this paper, we thus present a new model of coalition formation with possibly overlapping coalitions under partial information, where selfish agents may be part of multiple coalitions simultaneously and their full preferences are initially unknown. Instead, information about past interactions and associated utility […]

Ver mais

I’m occasionally accused of using LLMs to write the content on my blog. I don’t do that, and I don’t think my writing has much of an LLM smell to it… with one notable exception: # Finally, do em dashes s = s.replace(‘ – ‘, u’u2014’) That code to add em dashes to my posts dates back to at least 2015 when I ported my blog from an older version of Django (in a long-lost Mercurial repository) and […]

Ver mais

We coined a new term on the Oxide and Friends podcast last month (primary credit to Adam Leventhal) covering the sense of psychological ennui leading into existential dread that many software developers are feeling thanks to the encroachment of generative AI into their field of work. We’re calling it Deep Blue. You can listen to it being coined in real time from 47:15 in the episode. I’ve included a transcript below. Deep Blue is a very real issue. […]

Ver mais

We introduce Machine Learning as a Tool (MLAT), a design pattern in which pre-trained statistical machine learning models are exposed as callable tools within large language model (LLM) agent workflows. This allows an orchestrating agent to invoke quantitative predictions when needed and reason about their outputs in context. Unlike conventional pipelines that treat ML inference as a static preprocessing step, MLAT positions the model as a first-class tool alongside web search, database queries, and APIs, enabling the LLM […]

Ver mais

Optimizing CUDA code across multiple generations of GPU architectures is challenging, as achieving peak performance requires an extensive exploration of an increasingly complex, hardware-specific optimization space. Traditional compilers are constrained by fixed heuristics, whereas finetuning Large Language Models (LLMs) can be expensive. However, agentic workflows for CUDA code optimization have limited ability to aggregate knowledge from prior exploration, leading to biased sampling and suboptimal solutions. We propose KernelBlaster, a Memory-Augmented In-context Reinforcement Learning (MAIC-RL) framework designed to improve […]

Ver mais