February 2026

arXiv:2602.20163v1 Announce Type: new Abstract: Aphasia is an acquired language disorder caused by injury to the regions of the brain that are responsible for language. Aphasia may impair the use and comprehension of written and spoken language. The Western Aphasia Battery-Revised (WAB-R) is an assessment tool administered by speech-language pathologists (SLPs) to evaluate the aphasia type and severity. Because the WAB-R measures isolated linguistic skills, there has been growing interest in the assessment of discourse production as a […]

Ver mais

arXiv:2602.20162v1 Announce Type: new Abstract: Catastrophic forgetting remains a major challenge when fine-tuning large language models (LLMs) on narrow, task-specific data, often degrading their general knowledge and reasoning abilities. We propose SA-SFT, a lightweight self-augmentation routine in which an LLM generates self-dialogues prior to fine-tuning, and the resulting self-authored data are mixed with task data without modifying optimization or training schedules. Despite requiring no external data or additional tuning, SA-SFT consistently mitigates catastrophic forgetting while improving in-domain performance. […]

Ver mais

Checking agent outputs isn’t enough. The real failures hide in trajectories: which tools got called, in what order, with what inputs. This article walks through a pattern for building evals when you don’t have production data yet. You define the dimensions your agent varies along, generate structured tuples across them, and turn those into natural-language test queries. Run them, read the traces, write down what broke. Those notes become goals that shape the next batch of queries. Repeat […]

Ver mais

A paper from UGA shows you can match SOTA LLM performance with 2000 targeted samples instead of 300000. The secret? Looking inside model’s feature space. A recent paper called Less is Enough from University of Georgia, UC San Diego matched SOTA performance on instruction-following using 2,000 synthetic samples instead of 300,000. That’s 150x less data for the same results. The underlying idea is simple: two texts that look completely different can activate nearly identical features inside the model. […]

Ver mais

Last week, BBC journalist Thomas Germain wrote a fake blog post claiming he was the world’s greatest hot-dog-eating tech journalist. Within 24 hours, ChatGPT and Google were repeating it as fact. Claude, made by Anthropic, wasn’t fooled. One AI out of three caught the lie. The entire industry treated that as an interesting footnote. An engineer would call it the most important finding in the article. Two Inspectors Approved a Defective Part I am 75 years old. I […]

Ver mais

Written from the perspective of a senior engineer who has built, debugged, and battle-tested operators in production. Table of Contents Why Operators Exist The Conceptual Foundation: Control Theory Kubernetes API Machinery: The Backbone Custom Resource Definitions (CRDs) The Controller Runtime: Inside the Engine Informers, Listers, and the Cache The Reconciliation Loop in Depth Work Queues and Rate Limiting Watches, Events, and Predicates Ownership, Finalizers, and Garbage Collection Status Subresource and Conditions Generation vs ObservedGeneration: A Deep Dive Concurrency, […]

Ver mais

The Flexible Job Shop Problem (FJSP) is a well-studied combinatorial optimization problem with extensive applications for manufacturing and production scheduling. It involves assigning jobs to various machines to optimize criteria, such as minimizing total completion time. Current learning-based methods in this domain often rely on localized feature extraction models, limiting their capacity to capture overarching dependencies spanning operations and machines. This paper introduces an innovative architecture that harnesses Mamba, a state-space model with linear computational complexity, to facilitate […]

Ver mais

Claude can code, but can it check binary executables? We already did our experiments with using NSA software to hack a classic Atari game. This time, we want to focus on a much more practical task — using AI agents for malware detection. We partnered with Michał “Redford” Kowalczyk,a reverse engineering expert from Dragon Sector, known for finding malicious code in Polish trains, to create a benchmark of finding backdoors in binary executables, without access to source code. […]

Ver mais

It’s also reasonable for people who entered technology in the last couple of decades because it was good job, or because they enjoyed coding to look at this moment with a real feeling of loss. That feeling of loss though can be hard to understand emotionally for people my age who entered tech because we were addicted to feeling of agency it gave us. The web was objectively awful as a technology, and genuinely amazing, and nobody got […]

Ver mais

Not everything that can be automated should be. As QA engineers and leads, we often face the same question: Should we automate this, or handle it manually? And the truth is – there’s no single answer. The right choice depends on context, stability, and value. Automation is powerful when it accelerates learning and confidence, not just when it replaces human effort. But manual testing is equally valuable when it provides context, empathy, and deep insights that automation can’t […]

Ver mais