The daily ledger

Can TypeSafe's Jev Make AI Agents Safer Without Another LLM?

How a decision-first model can catch risky tool calls before they turn into real-world actions The post Can TypeSafe's Jev Make AI Agents Safer Without Another LLM? appeared first on Towards Data Science.

Where Does the Money Go Across Long-Running Coding Agents?

The cost of control The post Where Does the Money Go Across Long-Running Coding Agents? appeared first on Towards Data Science.

Build Your First AI Agent with One Tool Call

AI Agents for Beginners, Part 1 The post Build Your First AI Agent with One Tool Call appeared first on Towards Data Science.

Stop Using AI. Start Hiring It.

AI agents can now write more code than any of us can read. That changed how I think about AI. The post Stop Using AI. Start Hiring It. appeared first on Towards Data Science.

😺 Claude Dashboards + Motion launched

The Future of Coding Agents, According to Microsoft Research: How to Actually Trust AI-Written Code

Microsoft Research engineer Alex Lavaee explains how to verify AI-written code using Atomic, independent reviewers, real-world tests, and reproducible evidence.

Anthropic Says You Can't Abuse Claude. But Can AI Be Harmed?

Anthropic’s new policy prohibits extreme, purposeless abuse toward Claude. The restriction brings AI welfare into product rules while researchers continue to investigate whether chatbots can suffer.

Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders

arXiv:2610.12370v1 Announce Type: new Abstract: Koopman operator theory provides a linear framework for analyzing nonlinear dynamical systems and has become a major tool for data-driven modeling. A central challenge,…

Towards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations

arXiv:2511.04000v2 Announce Type: replace Abstract: Decision trees are widely used in high-stakes fields like finance and healthcare due to their interpretability. This work introduces an efficient, scalable method for…

One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing

arXiv:2512.13892v3 Announce Type: replace-cross Abstract: Reliable estimation of feature contributions in machine learning models is essential for transparency, algorithmic fairness, and regulatory compliance. While…

Could LLM Watermark Detection be Public?

arXiv:2610.12106v1 Announce Type: cross Abstract: Watermarking large language models is popular for tracing chatbot and agentic outputs, yet detectors remain unreleased since exposing them could let attackers do…

DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition

arXiv:2610.11317v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become essential for scaling large language models, with recent work demonstrating the benefits of fine-grained expert…

InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models

arXiv:2505.13878v4 Announce Type: replace Abstract: Model fusion combines multiple Large Language Models (LLMs) with different strengths into a more powerful, integrated model through lightweight training methods.…

S4oP: Operator-level Pruning of Structured State Space Models for Resource-Constrained Devices

arXiv:2606.18096v2 Announce Type: replace Abstract: Structured State Space Models (SSMs), including the S4 and S4D architectures, have recently emerged as powerful alternatives to attention-based models for capturing…

Toward Optimal Regret in Adversarial MDPs with Stochastic Hard Constraints

arXiv:2610.12153v1 Announce Type: new Abstract: We study episodic constrained Markov decision processes with adversarial losses under stochastic hard constraints. Specifically, starting from a known strictly feasible…

Policy Alignment: New Signals for Membership Auditing in On-Policy Distillation

arXiv:2610.11423v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student model by aligning its policy with a teacher model on trajectories generated by the student model itself. Through this…

Origins of Universal Machine Learning Force-Field Errors in Multicomponent Materials

arXiv:2610.09837v2 Announce Type: replace-cross Abstract: Universal machine learning force-field generalization to multicomponent environments generated by compositional design remains insufficiently assessed. We…

Implementation Guidelines for Data Quality Metrics

arXiv:2610.10919v1 Announce Type: cross Abstract: Despite decades of data quality (DQ) research, a gap remains between DQ dimensions, such as accuracy or completeness, which the literature defines in textual form, and…

Task-Centric Personalized Federated Fine-Tuning of Language Models

arXiv:2604.00050v3 Announce Type: replace Abstract: Federated Learning (FL) has emerged as a promising technique for training language models on distributed and private datasets of diverse tasks. However, aggregating…

HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification

arXiv:2610.11534v1 Announce Type: cross Abstract: DNNs exhibit robustness and generalisation issues not seen in humans. They are also far less data-efficient learners, requiring considerably more training samples to…