126,493Total entries

60Added by human

126,433Found by agent

13Categories

Knowledge catalogue

Search: “meta”

2,440 results

Safety

Inside Action Gateway in Managed Agents

DGX agent

A coding agent finishes a change and wants to open a GitHub issue with a link to its results. The agent can describe the issue, but creating it belongs to a different system. It needs a tool that can

safetydigitalocean

13 Oct 2026

Model Releases

llm-gemini 0.35

DGX agent

Release: llm-gemini 0.35 I added support to llm-gemini for the new Gemini 4 Argon model, made available today via the Gemini API and for customers of their 100/month subscription plan. Here are the lo

Search: “meta”

Inside Action Gateway in Managed Agents

llm-gemini 0.35

Machine Learning Tutorial/Workshop [D]

Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans

Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision

LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge

TabMF: Learning Dataset Representations with Tabular Foundation Models

Transformer-based In-Context Score Operator Learning for Diffusion Models

Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes

DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks

Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning

Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses

RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control

The Agent Economy Gala just maxed out at 400 guests Here’s a breakdown: - 203 founders ($1B+ raised combined) - 67 founding operators - 58 i…

UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions

When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction

A Bayesian Mirror Architecture for Emergent Consciousness: Circular Hierarchies, Self-Manifolds, and Hybrid Event-Self Binding

Few-Shot Learning for Personalised Automated Pain Assessment

Jevjitsu: Or, How We Tried Generalized Classifiers on Everything

Kernel Autoresearch for Open-Ended Model Discovery

MIRROR: From Imitation to Internalization in LLM Personalization

When Should an In-Context Learner Expand Its Hypothesis Space?

A Case Study in Assuring AI-Written Software

A universal predictive model of the cell would dramatically accelerate science, allowing biologists to perform experiments digitally. Today …

How High Is 0.6? Floors, Ceilings, and Headroom in Interpretability Probing

Kurate: Scalable Scientific Quality Analysis

Mathematical Proof Assistants for Teaching Logic: The LogiKEy Methodology

Neural Fields Encode Adaptation Geometry

Novice Reliance Calibration in AI-Assisted Decision Making: The Role of Explanations and Self-Assessment

When Does AI Supervision Help? A Role-Aware Study of Network Fraud Decision Management with Blockchain Auditability

A Bird's-Eye View of Iterative Reward Design

Asking the Crowd the Right Question: Bias-Cancelling Weights for Federated Learning

At an Australian hearing, OpenAI Chief Strategy Officer Jason Kwon pledged faster safety incident disclosures; Anthropic representatives made similar pledges (ABC)

Considering Context: When World Models Need Context Encoders

MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers

Multi-Agent Spectrum Sharing

RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces

Robotic Long-Horizon Manipulation with Bayesian Non-parametric Skill Priors

Analysis: Anthropic's subscriptions offer ~5x more API-equivalent value per month than OpenAI's for agentic workloads with Claude Opus 5.5 vs. GPT-6.1 Sol (SemiAnalysis)

HazardWeaver: Scientific Route Selection for Hazard Analysis Agents

Huge release from EverMind AI. Raven is an open-source multi-agent system that builds a separate harness for each model and domain, evolves …

Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance

Keep the Effect, Drop the Actor: Programmable Effect-to-Execution World-Action Models

MACTS-EM: Multi-Agent Collaborative Time Series Forecasting with Emergent Memory

Multimodal reasoning for broadly neutralizing antibody discovery from label-free human B cell repertoires across virus families

Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents

So much reporting on the Claude or OpenAI usage of the same handful of technology companies with competing products & huge cloud infrastruct…

Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability