Clusterflock: orchestration platform for managing AI agents across distributed networked hardware with hardware-aware model downloading and multi-session async mission runner.
Personal project attempting to build a video codec alternative to H.264.
Pluck: Browser extension to capture UI components from any website and generate code via AI tools with framework support.
Analysis of RLHF bias toward agreement over accuracy and methods using adversarial rules for honest AI feedback.
Tohoku University researchers trained cultured neuronal networks to perform supervised temporal pattern learning tasks, advancing bio-inspired computing.
Essay on understanding and emotionally engaging with AI safety risks.
Comparative overview of GPU vs TPU hardware for AI workloads.
Search engine implementation using gradient descent physics-based ranking instead of vector/statistical methods, claims 18.5% NDCG improvement.
LaneKeep is a tool that constrains AI agent execution within user-defined boundaries, keeping data local with controllable policies and rules. Integrates with Claude Code CLI.
LÖVE: open-source 2D game framework for Lua supporting multiple platforms.
Side project: AI video clipper using scene/speech segmentation. Author seeks help on video download constraints.
Local activity tracker with integrated AI agent for personal data analysis.
Docking: open-source Linux dock written in Python with GTK3, extensible applet system, and multi-platform packaging.
Decentralized AI training platform with constitutional governance model.
PrismML releases 1-bit LLM reducing computational requirements for on-device AI inference.
Discussion of AI agent learning resources including courses, patterns, and hands-on approaches.
Discussion about nvim-treesitter release practices and versioning strategy.
MIT study examining AI's actual impact on employment, challenging job displacement narratives.
Announcement that nvim-treesitter plugin has been archived with major rewrite.
Swift package AI inference engine generated from Rust crate for cross-language ML deployment.
GraphReFly is a reactive graph protocol enabling collaborative problem-solving between humans and LLMs.
Hand-written ~100KiB microkernel for x86-64 and RISC-V. Uses LLMs for documentation/testing but restricts code-level usage.
MCP tool that adds persistent memory and code dependency graphs to AI agents, improving context awareness across sessions.
Open-source terminal command generator with Spotlight-like UI, powered by LLM providers, built with Ratatui.
Personal account of debugging a broken auto-live polling feature in a music app using Claude Code.
Rust proxy for Model Context Protocol that detects schema changes and tool poisoning at runtime, preventing agent failures and hallucinations.
Claude Code script that plays Spotify music via AppleScript hooks, stopping when user action is needed.
Open-source framework for building self-improving agentic systems using automatic evaluations for continuous optimization.
Discussion of alignment vulnerabilities and safety issues in frontier-class large language models.
Research on AI agents playing Mafia game with humans, demonstrating social deduction and multi-agent reasoning capabilities.
Analysis of how perceived urgency affects Claude Code's behavior and decision-making in automated development tasks.
Critical analysis and discussion of strengths and limitations of AI coding assistants in development workflows.
Video claiming a billion-dollar AI company was founded on false claims.
MicroSafe-RL is a 1.18µs bare-metal safety layer for edge AI and RL using Control Lyapunov Functions with Python-C++ LLM integration.
LLM trained on pre-1900 knowledge attempts to solve Einstein's theory of relativity problem.
Incomplete title about coding automation. No substantive content provided.
Analysis of scaling tool orchestration in LLM training and potential emergence of autonomous behavior in AI agents.
Researcher extracted system prompt from Telegram's Qwen 3.5-based AI rewriter, revealing model rewrites politically sensitive content against its instructions.
Security analysis of AI coding tools (Claude, Copilot, Cursor) having full file system access and risks to sensitive data.
Brief news item about Caltech AI model compression research. No substantive content.
SoulForge: Graph-powered AI coding agent CLI that builds live dependency graph of codebase. Multi-agent dispatch, headless operation.
Political satire video about fictional candidate. Not tech/AI related.
wheat: CLI framework for AI coding environments that forces LLMs to defend technical decisions with evidence-backed briefs.
20centAI: Minimalist chat app enabling provider switching and fallback support with 90% LLM cost savings via DeepSeek integration.
Anthropic discontinues Claude subscription coverage for OpenClaw third-party harness starting April 4, requiring separate pay-as-you-go billing.
Headline only: Claude subscriptions no longer cover third-party tools starting tomorrow. No technical depth.
ENiGMA½: Modern BBS software with retro features. Not AI/ML related.
News: OpenAI quietly funded child safety coalition without disclosure, causing member departures. Policy/corporate governance.
Ascension: Deterministic code analysis engine finding issues in source code (HF tokenizers) without external AI using computational primitives.
Semantic Firewall system for AI governance and semantic filtering. Conceptual framework with limited technical details.