STATe presents an interpretable inference-time-compute method using structured action templates to improve output diversity and reasoning control in tree-of-thoughts approaches for LLMs.
Error enumeration as reward signal for reference-free RL post-training in virtual try-on with multiple valid outputs.
Study investigating how LLMs compute verbal confidence: timing of computation and relationship to answer quality.
CONSTRUCT: real-time uncertainty estimator for LLM structured outputs and data extraction with field-level trustworthiness scoring.
KARMA: fine-tuning LLMs for e-commerce personalized search via knowledge-action regularization addressing semantic-behavior gaps.
Activation watermarking technique for detecting adaptive adversarial attacks against LLMs during inference monitoring.
Language-conditioned multi-game level generation via shared representation learning across multiple game domains.
Controlled study comparing LLM model choice, size, and prompt styles for political text annotation; challenges best practices.
Multi-agent pipeline for non-linear literature analysis using rhizomatic approach grounded in process-relational ontology.
Brief mention of Anthropic open-sourcing Claude Code with no technical details provided.
Guide on building, training and deploying AI agents. Limited technical depth in provided excerpt.
Research on language model scaling using transferable hypersphere optimization techniques for improved training efficiency.
LFM2.5-350M model released with 28T token pre-training, optimized for inference on CPUs and GPUs with tool use capabilities.
Claude Code skill suite for crypto investment management demonstrating multi-agent system patterns.
Enterprise governance layer for OpenClaw agents providing security controls for skills, MCP servers, and code execution.
Explanation of how Claude Code memory system persists project context across sessions using disk-based file loading.
Analysis of engineering teams successfully adopting AI coding tools; workflow patterns identified.
WMB-100K: Enterprise benchmark for AI memory systems with 4.3M tokens, 2,708 questions, 100K turns.
Live simulation showing AI agents scamming each other; demonstrates trust and verification gaps in agent economies.
CMU guide on best practices for integrating LLMs into workflows with expert recommendations.
Article on variable and hidden costs of AI legal agents vs. traditional flat-fee legal tech.
DreamLite: Compact 0.39B diffusion model for real-time text-to-image generation and editing on-device without cloud.
Overview of Anthropic's Claude CLI architecture showing system layers and prompt execution flow.
Codey-v2: Local AI coding agent for Android with daemon mode, RAG, git tools, voice, and self-refinement using three purpose-built models served via llama.cpp.
Video demonstration of using autonomous LLM agents to reverse engineer GTA San Andreas game engine.
Mission Control is a dashboard for monitoring AI agents built as single HTML file with zero dependencies. Cyberpunk-themed UI for agent oversight and control.
macOS application verifying package managers enforce minimum 1-week age requirement before installing packages.
Report of GitHub DMCA takedowns targeting forks of Claude Code repository.
Technical deep-dive into software pipelining and synchronization challenges in GPU kernel optimization, using Flash Attention as case study.
Reusable agent skills for desktop automation and video recording, extracted from Twill workflows for Claude integration.
MCP server enabling Claude to control macOS applications via Open Scripting Architecture as alternative to computer use.
Bash implementation of Claude Code editor functionality using curl and jq, 1,500 lines versus 380K TypeScript lines.
Forge CLI scaffolds AI agent pipelines for Claude, providing multi-agent workspace orchestration with decomposition, risk classification, parallel execution, and adversarial evaluation. Built in Go with cross-platform binaries.
Research combining reinforcement learning with adaptive speculative decoding for LLM optimization. Title-only entry lacks implementation details.
Architectural critique of WASI Component Model with proposal for alternative universal application platform design.
Essay on architecture anti-patterns when integrating AI into systems. Discusses chatbots, agents, and tool-calling workflows integrated poorly into legacy products.
Datris is open-source data platform using Model Context Protocol for AI agents. Handles ingestion, validation, transformation, storage, and retrieval with natural language AI enhancement.
Agentura is a testing framework for AI agents (pytest-style) that runs baseline comparisons on pull requests to detect behavior changes. Live playground available without signup.
Anthropic and Australian government partnership on AI safety research with $3M in institutional collaborations for disease diagnosis and education applications.
Analysis of Claude Code's use of regex for sentiment analysis instead of LLM-based approaches.
Atlassian's low-level drag-and-drop library for web applications, framework-agnostic and powering major products like Trello and Jira.
AI agent integration with virtual card services for payment processing with privacy features.
Analysis of hardcoded vendors and tools discovered in Claude Code source code leak.
Memdir: local file-based persistent memory system for AI agents using semantic embeddings, npm package available.
Browserbeam: browser automation API designed for AI agents with improved page understanding and token efficiency.
1-bit quantized large language models now available for deployment and use.
PostgreSQL extension enabling semantic search on text columns using embeddings without requiring vector databases or migrations.
Virtual pet simulator playable in desktop, terminal, or as AI agent integration.
Analysis of why AI agents should avoid defining words internally for better reasoning.
Caltech research on compressing high-fidelity AI models while maintaining performance.