February 2026

Existing Graphical User Interface (GUI) agents operate through step-by-step calls to vision language models–taking a screenshot, reasoning about the next action, executing it, then repeating on the new page–resulting in high costs and latency that scale with the number of reasoning steps, and limited accuracy due to no persistent memory of previously visited pages. We propose ActionEngine, a training-free framework that transitions from reactive execution to programmatic planning through a novel two-agent architecture: a Crawling Agent that constructs […]

Ver mais

Table of Links Abstract and 1. Introduction 2. Financial Market Model and Worst-Case Optimization Problem 3. Solution to the Post-Crash Problem 4. Solution to the Pre-Crash Problem 5. A BSDE Characterization of Indifferences Strategies 6. The Markovian Case 7. Numerical Experiments Acknowledgments and References Appendix A. Proofs from Section 3 Appendix B. Proofs of BASDE Results from Section 5 Appendix C. Proofs of (CIR) Results from Section 6 6. The Markovian Case The last proposition associates the indifference […]

Ver mais

Table of Links Abstract and 1. Introduction 2. Financial Market Model and Worst-Case Optimization Problem 3. Solution to the Post-Crash Problem 4. Solution to the Pre-Crash Problem 5. A BSDE Characterization of Indifferences Strategies 6. The Markovian Case 7. Numerical Experiments Acknowledgments and References Appendix A. Proofs from Section 3 Appendix B. Proofs of BASDE Results from Section 5 Appendix C. Proofs of (CIR) Results from Section 6 5. A BSDE Characterization of Indifference Strategies In the previous […]

Ver mais

Table of Links Abstract and 1. Introduction 2. Financial Market Model and Worst-Case Optimization Problem 3. Solution to the Post-Crash Problem 4. Solution to the Pre-Crash Problem 5. A BSDE Characterization of Indifferences Strategies 6. The Markovian Case 7. Numerical Experiments Acknowledgments and References Appendix A. Proofs from Section 3 Appendix B. Proofs of BASDE Results from Section 5 Appendix C. Proofs of (CIR) Results from Section 6 4. Solution to the Pre-Crash Problem It is now left […]

Ver mais

Safety Is Not a Switch, It Is a Process For a long time, AI safety seemed like something you could install. You specified constraints, tested for edge cases, built guardrails, and deployed with confidence. This paradigm was fine when systems were largely static. It starts to break when systems change. Today, AI systems do not merely follow pre-programmed logic. They learn. They adapt. They interact with other agents. In multi-agent settings, systems negotiate, compete, coordinate, and sometimes, game […]

Ver mais

I was doing some research today and ran into a couple instances where part of one law was copied and pasted verbatim into another law. I suppose this is not uncommon, but I’m not a lawyer, so I don’t have that much experience comparing laws. I do, however, consult for lawyers and have to look up laws from time to time. Here’s an example from California Health and Safety Code § 1385.10 and the California Insurance Code § […]

Ver mais

Federated Learning (FL) enables a distributed client-server architecture where multiple clients collaboratively train a global Machine Learning (ML) model without sharing sensitive local data. However, FL often results in lower accuracy than traditional ML algorithms due to statistical heterogeneity across clients. Prior works attempt to address this by using model updates, such as loss and bias, from client models to select participants that can improve the global model’s accuracy. However, these updates neither accurately represent a client’s heterogeneity […]

Ver mais

Unprocessed emotions act like background apps hogging your brain’s limited working memory, slowing you down even in quiet moments. This fresh lens recasts cognitive overload as emotional RAM drain—and introduces introspection as the ultimate cleaner. Some cognitive models suggest that unprocessed emotions can waste 20–30% of our thinking bandwidth. It’s like trying to ship code while a background process silently occupies one-third of your CPU. This “emotional residue”—the stuff we suppress to get through the day—doesn’t go away; […]

Ver mais

I Built ArtemisFlow: A Local-First Job Tracker for Tech Candidates Modern hiring processes often involve multiple companies, stages, and timelines happening in parallel. At some point, keeping track of everything becomes harder than it should be. Like many developers, I initially used spreadsheets. They worked well enough in the beginning. But over time, they became harder to maintain. I kept adding columns, moving things around, and writing notes in places that didn’t really belong anywhere. Some companies replied […]

Ver mais

Ver mais