Higher-Order Token Interactions via Quantum Attention
Quantum Higher-Order Attention mechanism for computing higher-order token interactions beyond pairwise relationships in transformers.
Quantum Higher-Order Attention mechanism for computing higher-order token interactions beyond pairwise relationships in transformers.
Uses LLMs via in-context learning to generate synthetic ground truth labels for training audio-based emotion classification models.
Multimodal graph neural network system for precipitation nowcasting combining radar, weather prediction, and sparse point observations.
OpenAnt framework uses LLMs for automated vulnerability discovery in code repositories via semantic reasoning, decomposition, and adversarial verification.
Automated annotation framework using machine learning to handle extreme class imbalance in Autonomous Emergency Braking system event labeling.
TxBench-PP benchmark for evaluating AI agents on small-molecule preclinical pharmacology tasks in drug discovery with verifiable, realistic decision-making scenarios.
Iamspeed.dev is a speed testing tool for LLMs, similar to Fast.com but measuring language model performance.
Agent Finder: search interface implementing Agentic Resource Discovery specification; catalog of Azure skill definitions for agent integration.
BeamWeaver: Elixir framework for building agents and agentic workflows inspired by LangChain/LangGraph. Features tool calling, graph workflows, checkpoints, memory, and provider adapters.
Protocol-level defense against MCP tool poisoning. Proposal and reference implementation for optional cryptographic signing of tool manifests to prevent modification after approval.
Datasette-apps: plugin enabling custom HTML/JavaScript applications to run in iframe sandbox within Datasette, with read/write SQL query support.
Educational article explaining how LLMs work, covering terminology and practical applications in coding, document summarization, and autonomous agents.
Flashback: agent skill providing searchable historical design trends database from 1900-present as reference resource for design-related agent tasks.
Drydock: VM sandbox system for running autonomous coding agents (Claude, OpenAI) locally on macOS with hardware isolation, token gating, and deny-by-default egress.
Case study testing whether candidates with outdated tech stacks but active AI tool usage can pass standard hiring processes at software companies.
Agent-powered code modification system. Users request changes on live websites; coding agent implements changes, generates preview, and creates pull request for approval.
Hermzner: provisioning tool for deploying Hermes Agent on Hetzner VPS with security hardening, Tailscale integration, backups, and optional Mnemosyne memory provider.
OpenMontage: open-source agentic system for video production. Users describe desired output in natural language; agent handles research, scripting, asset generation, editing, and composition.
bote library processes large JSON files with low memory footprint using cursor-based streaming and path queries.
Pagecast CLI tool for publishing Claude Code/Codex-generated HTML/Markdown reports to Cloudflare Pages.
Elastic Agent Builder provides persistent memory layer for agents using hybrid retrieval, reranking, and decay mechanisms.
GLaDOS personality plugin with neural TTS for Claude Code using Forward Tacotron and HiFiGAN.
Deep dive on integer quantization for transformers, covering techniques for fitting large models in 4-bits on single GPU.
Blog post on building AI agents in Go without frameworks, explaining why Go's runtime fits agent architecture and surveying framework options.
Open-source local debugging agent that captures unsampled production runtime data and routes it to coding agents to generate fixes automatically.
Ironsmith open-source macOS app for generating native SwiftUI applications using local LLMs via natural language descriptions.
Language1 benchmark game testing LLM comprehension through reverse Taboo word game with forbidden terms.
Git diff filter using Claude to annotate code changes with inline explanations for code review and understanding.
Layr production constraint system converting AI-generated interfaces into production-grade apps with design and UX principles.
Open-source DSL for building fully-homomorphic encryption apps with client-side IR compilation and server-side optimization.
Discussion questioning whether matrix multiplication is necessary for intelligence or if sparse signal routing could achieve AGI more efficiently.
sx tool for managing coding agent skills, tools, and rules at scale across organizations with centralized syncing and backup.
OpenAI announces GPT-5.5 Instant with improved health intelligence capabilities for ChatGPT, used by 230M weekly users for health questions and medical information.
Self-healing CI/CD system for AI agents as GitHub App with Python support. Working tool for agent deployment.
Research on auditing LLM agents and upstream data feeds. Abstract only, no technical depth.
Plugin for reducing token usage with Claude Code. Minimal details provided.
Framework for formal governance mechanisms in multi-agent systems.
Guide on integrating payment processing into MCP tools. Limited technical depth in description.
Unreal Engine 5.8 integrates MCP (Model Context Protocol) server support for AI agents.
AI agent system that autonomously organizes Obsidian note vault.
Philosophical discussion on agentic AI and what remains distinctly human. Conceptual rather than technical.
Historical piece on SmarterChild chatbot predating ChatGPT. Personal anecdote mixed with technical history.
SaaS platform built 8 AI tools (resume scanner, interview prep, cover letter generators) using Nvidia NIM with $0 API costs. Includes production architecture details.
Open-source multi-modal AI workflow studio with visual interface. Developer tool for building AI applications.
Open-source LLM fusion tool combining multiple models for complex queries and tool calling.
CLI tool enforcing spec-driven development with Claude Code, OpenCode, and Codex LLM models. Limited details.
Discussion on detecting LLM API performance degradation and model drift in production systems.
Stack Overflow launches beta platform specifically designed for AI agents to query technical knowledge base, extending 15+ years of peer-validated developer Q&A.
Kolmogorov-Arnold Networks for ultrafast on-chip online learning with sub-microsecond latency for quantum and fusion control systems.
Domain generalization approach leveraging unlabeled data in anti-causal settings where outcomes cause observed covariates.