Newest · pág. 15

← primera página

On Bergman’s *Persona*
Marginal Revolutionmarginalrevolution.comAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 6:53:12detalle
Cómo convertí mi repo de skills en un marketplace de Claude Code
Marcos Ramírezblog.marcosramirez.infoAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 6:30:00detalle
El regreso de los pingüinos
Enrique Dansenriquedans.comAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 6:19:15detalle
Lean now ships with verified kernels
Hacker Newsleodemoura.github.ioAgregado: 18/10/2026, 18:00:49Publicado: 16/10/2026, 6:16:13detalle
Why are we even doing all this?
Lobste.rsterrytao.wordpress.comAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 5:28:29detalle
I guest host the NYT podcast and interview Dwarkesh
Marginal Revolutionmarginalrevolution.comAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:44:22detalle
Meetups Everywhere 2026: Times & Places
Astral Codex Tenastralcodexten.comAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:04:26detalle
OTel: Open Telco AI Datasets, Benchmarks, and Models
arXiv cs.AIarxiv.orgAgregado: 7/10/2026, 4:00:43Publicado: 16/10/2026, 4:00:00detalle
Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 16/10/2026, 4:00:00detalle
ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding
arXiv cs.AIarxiv.orgAgregado: 7/10/2026, 4:00:43Publicado: 16/10/2026, 4:00:00detalle
Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
arXiv cs.AIarxiv.orgAgregado: 9/10/2026, 4:00:53Publicado: 16/10/2026, 4:00:00detalle
SCOPE: Certified Theorem Proving with a Language Model as the Policy Planner
arXiv cs.AIarxiv.orgAgregado: 7/10/2026, 4:00:43Publicado: 16/10/2026, 4:00:00detalle
Minimal Witness Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 7/10/2026, 4:00:43Publicado: 16/10/2026, 4:00:00detalle
E$^2$-OPSD: Taming Entropy Overshoot in On-Policy Self-Distillation
arXiv cs.AIarxiv.orgAgregado: 7/10/2026, 4:00:43Publicado: 16/10/2026, 4:00:00detalle
KV$^2$: A Self-Refining KV Cache
arXiv cs.AIarxiv.orgAgregado: 5/10/2026, 4:00:48Publicado: 16/10/2026, 4:00:00detalle
Video-Time Priors for EEG-fNIRS Emotion Regression on Familiar Videos
arXiv cs.AIarxiv.orgAgregado: 5/10/2026, 4:00:48Publicado: 16/10/2026, 4:00:00detalle
ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe
arXiv cs.AIarxiv.orgAgregado: 5/10/2026, 4:00:48Publicado: 16/10/2026, 4:00:00detalle
From Migration to Calibration: Aligning Agents with Deployment Requirements
arXiv cs.AIarxiv.orgAgregado: 5/10/2026, 4:00:48Publicado: 16/10/2026, 4:00:00detalle
The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Evaluating Model Capabilities After Benchmark Saturation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
When Correctness Feedback Erases Evidence: Phase-Separated Completeness Auditing in Verus
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
IneqAgent: Agentic Inequality Proving in Lean with Symbolic Computation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
L2G-SR: Learning to Guide LLM-based Symbolic Regression
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
When Reality Outpaces Cognition: A New Scaling Principle for Reliable Intelligence
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
ARIA: Runtime Inspection and Amendment for Multi-Agent Systems
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Open-world AI: a Tale of Three Requirements
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open Worlds
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
When Reasoning Traces Conflict with Evidence: How Answer Configuration Shapes Evidence Following
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Temporal Specification Guidance for Text-to-Video Generation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Anticipatory Commonsense with Moving Objects: An ASP-Based Framework for Predictive Reasoning with Interacting Trajectories
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
A Multi-Tiered AI Accessibility Model (MAIAM): Proportionate Access and Capability Limits for Comprehensive Frontier AI Safety
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Defining and Generating Compositional Structure
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
RAC: A Relational Agent Contract for Constraint-Governed Engineering Tasks
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
LEV: Thinking Fast and Deep with Looped Decision Models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
StepSafe: Learning Timely Intervention with Context-Aware Safety Reasoning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Deep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Failure Is the Mother of Success: Recovering Supervision with Grounding Hindsight
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Recursive Reward Improvement via Adversarial Meta-Prompt Evolution
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Learning When to Withdraw: Curriculum Coverage and Rule-Specific Failures in Fine-Tuned Language Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Athanor: An Agent-Native System for Autonomous Post-Training Research
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
OmicsBench: a long-horizon multi-turn benchmark of AI agents on research-study-scale bioinformatics
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle