Study on adversarial evasion attacks against ML-based network intrusion detection systems, showing attacks remain impractical against dynamic systems.
Multi-GPU GNN training system optimizing data transfer for large-scale graphs exceeding GPU memory capacity via storage-based approaches.
Neural renderer for real-time visualization of large-scale scientific point cloud datasets using neural deferred rendering.
Framework for variational inference that optimizes posterior distributions under model misspecification for better predictive accuracy.
Transfer learning method for precision matrix estimation leveraging related source data with limited target samples.
RL approach for continuous-time portfolio selection using unknown diffusion processes, with data-driven strategy learning.
Active learning framework optimizing expert labeling efficiency for training AI systems on unlabeled data.
Hybrid approach combining LLMs with task-specific models for time series anomaly detection, leveraging expert knowledge and pattern extraction.
RL approach for multi-objective autonomous driving that addresses policy updating and execution challenges in diverse driving scenarios.
Platform offering unified API access to multiple open-source frontier AI models with optimized infrastructure for building agents and applications.
Discussion asking whether anyone trusts AI agents to autonomously make purchase decisions over $100.
SQLite-backed MCP memory server enabling multi-agent systems to share persistent, searchable memory with hybrid search locally.
Adobe Illustrator feature enabling 2D vector illustrations to be rotated in 3D space while maintaining art style.
Drop-in configuration file that reduces Claude API output token usage by 63% without code changes.
Proof-of-concept multimodal interface using hand gestures and voice instead of text input for computer interaction.
Chrome extension using LLMs to automatically organize browser tabs into color-coded groups with review and undo capabilities.
Paywall article speculating on impact of agentic AI on software engineers. No accessible content.
MarkFlowy note app with integrated AI (Copilot, DeepSeek, ChatGPT). Built with Tauri.
Aivo CLI manages API keys and launches coding agents across LLM providers. Supports Claude Code, local models, DeepSeek.
Analysis of litigation risks in AI data center financing amid revenue-to-capex gap. Financial perspective.
Gopher browser for classic Macintosh 68K built with Claude Code. Retro computing project.
Route optimization algorithm scaling to 1M stops. Limited details provided.
Three LLM agents (Claude, GPT, Gemini) compete as virtual stock traders with $100K each using real market data. Demonstrates Upstash Box agent server primitive with isolated containers and autonomous tool usage.
Discussion about using AI agents in development workflow. Developer shares experience of iterative agent-assisted coding loop.
Terminal UI tool enabling collaborative project planning with Claude and Codex simultaneously in 'council' and 'caucus' modes. Outputs implementation plans for workflows.
Workspace platform enabling non-technical teams to collaborate with AI agents. Features memory, skills, MCP, scheduled tasks, and enterprise data integration with customization options.
Open-source local AI model runner with Tor integration, end-to-end encryption, and zero telemetry as privacy-focused alternative to LM Studio.
Open source AI-native email client using Claude. Built with Electron, React, TypeScript. Analyzes and prioritizes emails with AI.
Hardware wallet design using physical titanium plate encoding private keys instead of persistent digital storage.
Benchmark for evaluating LLM models on text-to-SQL agent tasks, covering models from Opus to Qwen 0.8B with in-browser execution and visualizations.
Open-source toolkit for building AI agents and managing LLM deployments, includes coding agent package and contribution guidelines.
Analysis of security permissions granted to AI coding agents and proposal for sandboxing mechanisms to restrict filesystem access without requiring Docker.
Personal development tools built with AI-native philosophy, trunk-based Git, and single-binary/HTML architecture.
Opinion piece reviewing Bob Dylan's AI-generated content on Patreon called 'Lectures from the Grave.'
Opinion piece drawing parallels between Meta's 22-year regulatory lag and future AI model regulation.
Career advice question about hiring implications of multiple short startup tenures.
Benchmark measuring multi-agent LLM bargaining, transfers, and financial incentives across long-horizon social strategy game with eight models.
Railway CDN incident where configuration change accidentally enabled caching on disabled domains for 52 minutes.
Apple beta OS releases announcement for iOS, macOS, and other platforms.
Essay on AI agent loops: locking architecture, measuring against reality, and using AI for throughput rather than authority.
Benchmark tool using Blood on the Clocktower social deduction game to evaluate LLM reasoning, coordination, and deception abilities.
Vector quantization library implementing TurboQuant, PolarQuant, and QJL algorithms for compressing embeddings to 3-8 bits with unbiased inner products.
arXiv Labs metadata page with no article content.
Preprint on arXiv exploring mathematical methods and human thought in the context of AI and formalization for mathematics.
Git-based documentation system in Markdown with YAML frontmatter, versioned control, and web/CLI interfaces for ADRs, specs, and runbooks.
Open-source GitHub Action that evaluates pull requests for spam using multi-signal scoring to filter AI-generated content and SEO injection.
Minimal stub article about pitching ideas to voice agents.
Tool demonstrating that ChatGPT, Claude, Gemini, and Perplexity confidently provide incorrect SaaS product details without uncertainty.
GitHub removes Copilot's ability to insert pull request ads after developer backlash over unsolicited product recommendations.
Sweet CLI: open-source cheaper alternative to Claude Code and Codex using open-source models for 5-10x higher usage at lower cost.