arXiv:2602.18571v1 Announce Type: new Abstract: While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime behavior remains largely a manual, developer-driven process. Popular coding agents typically rely on either static analysis of the code or iterative test-fix cycles, which is akin to trial and error debugging. We posit that there is a wealth of rich […]

Ver mais

arXiv:2601.07964v1 Announce Type: new Abstract: This paper examines the application of Executable Ontologies (EO), implemented through the boldsea framework, to game development. We argue that EO represents a paradigm shift: a transition from algorithmic behavior programming to semantic world modeling, where agent behavior emerges naturally from declarative domain rules rather than being explicitly coded. Using a survival game scenario (Winter Feast), we demonstrate how EO achieves prioritybased task interruption through dataflow conditions rather than explicit preemption logic. Comparison […]

Ver mais

arXiv:2601.09001v1 Announce Type: new Abstract: Deploying LLMs raises two coupled challenges: (1) monitoring – estimating where a model underperforms as traffic and domains drift – and (2) improvement – prioritizing data acquisition to close the largest performance gaps. We test whether an inference-time signal can estimate slice-level accuracy under domain shift. For each response, we compute an output-entropy profile from final-layer next-token probabilities (from top-k logprobs) and summarize it with eleven statistics. A lightweight classifier predicts instance correctness, […]

Ver mais

I Fine-Tuned BERT 47 Times Before I Realized I Was the Problem Fine-tuning BERT looks simple on Hugging Face. Running it in production looks like a different universe. Attempt number 47. Surely the learning rate is the only variable left to change. It was 1:47 AM. The sprint demo was in six hours. I had a BERT model fine-tuned on our customer support ticket dataset. I’d done everything by the book. Pre-trained weights from bert-base-uncased. Hugging Face Transformers. AdamW optimizer. Learning rate […]

Ver mais

arXiv:2601.21083v1 Announce Type: new Abstract: As large language models improve, so do their offensive applications: frontier agents now generate working exploits for under $50 in compute (Heelan, 2026). Defensive incident response (IR) agents must keep pace, but existing benchmarks conflate action execution with correct execution, hiding calibration failures when agents process adversarial evidence. We introduce OpenSec, a dual-control reinforcement learning environment that evaluates IR agents under realistic prompt injection scenarios. Unlike static capability benchmarks, OpenSec scores world-state-changing containment […]

Ver mais

Anthropic’s AI chatbot Claude experienced a widespread outage on Monday, March 2, 2026. Over on Downdetector, users reported a spike in error rates yesterday morning. Many users complained about seeing HTTP 500 and 529 errors, login loops, slow responses, and complete denial of service when trying to interact with Claude’s web and mobile app. However, Anthropic restore the issue later yesterday. Claude AI faces outage two days in a row However, it seems the issue related to Claude […]

Ver mais

This paper introduces a biomimetic framework and novel brain-inspired AI (BIAI) models based on spiking neural networks (SNNs) for emotion recognition from audio (speech), visual (face), and integrated multimodal audio-visual data. The developed framework, named eXCube2, uses a three-dimensional SNN that is spatially structured according to a human brain template. The BIAI models developed in eXCube2 are trainable on spatio- and spectro-temporal data using brain-inspired learning rules. Such models are explainable in terms of revealing patterns in data […]

Ver mais

Hi everyone, I’ve written a short research note on GitHub where I explore an idea related to making LLMs improve their own training process by self-distribution aware analysis. The focus is not on a specific implementation, but on a general training paradigm and how models could guide what data or signals they learn from next. I’m looking for feedback or criticism. My goal is discussion and learning, not making any strong claims. If someone finds the direction interesting […]

Ver mais