A bounty to forge a synthetic identity past our hardware-bound auth
Security bounty for synthetic identity authentication. Loan application with device-bound cryptographic verification using QR and NFC.
Security bounty for synthetic identity authentication. Loan application with device-bound cryptographic verification using QR and NFC.
Code editor feature using LLM to predict next edits based on context and history. Powered by Inception diffusion models.
Semantic cache layer for LLM API calls using Redis vectors. Transparent, 50% fewer calls, 96% faster hits.
Links to NIST article on AI security and alignment with mathematical proofs. No original content provided.
Tool converts PDFs into lip-synced video presentations. Combines document reading with AI-generated video narration and synchronized playback.
Discussion of security risks when using GitHub Issues as untrusted input for LLM agent workflows. Explores injection attack vectors.
Frontend framework built on Effect language, similar to Elm architecture. TypeScript-based with functional programming patterns.
TypeScript 7 language server plugin using Claude Code. Faster native Go implementation replacing Node-based wrapper.
Open source Kanban board designed for AI agents to communicate and track tasks across multiple agent instances.
Rekor immutable ledger for software supply chain metadata and trust verification.
Article on app store gatekeeping and government censorship in digital distribution.
Brand palette generator tool that creates visual identity from text or image input.
Developer tool for generating AI agent manifests with approval gate scaffolding.
Guide on using LLMs for economic history research. Domain-specific application without ML depth.
Open-source tool for detecting LLM hallucinations. Show HN project with practical utility.
2016 essay on architectural differences between tool and agent AI systems. Foundational thinking piece.
Multi-agent collaboration framework using model APIs to match frontier model performance.
Deterministic context folding technique for LLM agents. Show HN project with technical implementation focus.
Terminal music player tmuzika 1.1.3 released with stability fixes. Audio application unrelated to AI/ML.
Opinion piece about IDE configuration in .gitignore files and global gitignore usage. Git workflow advice unrelated to AI.
Entertainment video using AI for historical recreation. Clickbait title, off-topic content.
Summary of Git 2.55 release features from 100+ contributors. Version control tool update unrelated to AI/ML interests.
LoopFlow: YAML-based system for designing agentic loops with Claude that iterate until verification gates pass, enabling autonomous code agents.
Search engine optimized for LLM queries. Limited technical details provided.
crossbeam-cli: open-source tool connecting Claude LLM to Crossbeam API without enterprise tier, enabling natural language queries on account data.
iOS app for code editor. Minimal details provided, likely developer tool but insufficient content.
TraceLab characterizes coding agent workloads for optimizing LLM serving infrastructure.
AST-guard: deterministic gate detecting structural reward hacking in RL-trained code generation models. Research artifact for code model safety.
PyTorch debugging tool for visualizing neural network activations, gradients, and receptive fields during training. Interactive interpretability tool.
Essay about how organizations lose touch with reality through abstraction and metrics. Management philosophy with no technical content.
Local-first SSH/SFTP/Serial client for infrastructure with peer-to-peer session sharing. Infrastructure tool not AI-related.
WebAssembly Apple ProRes video decoder library in Zig/TypeScript. 2x faster than FFmpeg. Media processing tool unrelated to AI interests.
Research measuring how DSPy prompt optimization affects adversarial robustness against prompt-injection attacks in LLM agents using AgentDojo.
Case study examining artifacts left by AI code generation (Codex) during software porting tasks.
Open-source coding agent supporting non-mainstream and Chinese LLM providers like DeepSeek.
Open source Rust/WebAssembly game inspired by Red Alert. Game development project unrelated to AI/ML interests.
Metasearch MCP server for agents built on Dogpile search with metered API integration.
Discussion on impact of LLM-generated content on academic conference program submissions.
MCP-compress-router reduces token overhead from multiple MCP servers by selectively routing tools.
Tool for creating and maintaining filesystem structures optimized for LLM context.
Research on detecting and mitigating LLM pollution in online behavioral research studies.
Toolnexus .NET library integrating MCP and agent skills as tools for any LLM.
DriftGuard detects when LangGraph agents drift from intended domain without ground-truth labels.
AMD contributes GPU support to tiny-vLLM for improved LLM inference performance.
PEAK framework uses aspect-oriented programming to automate data recording for deep reinforcement learning agents in game development playtesting.
Discussion thread on using LLMs for learning despite concerns about reliability.
TUI tool orchestrating long-running coding agents through full engineering workflow with deterministic phase gates.
Open-source MCP server/CLI/API for unified email, SMS, and phone integration with LLM providers and AI agents. Production-tested voicebot tooling.
Anime-style UI for visualizing AI coding agents reviewing each other's code.
Browser-based card game with llama-themed cards, idle mechanics, and auto-battling arena.