MSA: Memory Sparse Attention
MSA proposes a scalable latent-memory framework enabling 100M-token context windows for LLMs, addressing attention bottleneck limitations.
MSA proposes a scalable latent-memory framework enabling 100M-token context windows for LLMs, addressing attention bottleneck limitations.
Title only, no content. About intelligent routing for LLM requests.
Andrej Karpathy discusses AI agents, autonomous research systems, and the future of coding in a video presentation.
Essay discussing LLMs' impact on writing and language. Philosophical, not technical research.
Using local LLMs with Ghidra reverse engineering tool for malware analysis and code understanding.
Security analysis of risks from LLM-generated administrative scripts in privileged production environments.
Autoskill enables AI agents to self-improve and learn new capabilities iteratively during operation.
Windows Subsystem for Linux graphics driver improvements for GPU support in Linux applications.
Philosophical discussion questioning whether true AI alignment is logically achievable or paradoxical.
Conductor framework for deterministic routing and coordination in multi-agent AI workflows.
Analysis of data centers as military targets following Iran's counterattack on US-linked infrastructure.
System orchestrating Claude and OpenAI Codex as collaborative coding agents using existing subscriptions without additional API costs.
OpenClaw deterministic security solution for constraining AI agent capabilities with rule-based access controls.
Storage engine for MariaDB with ACID transactions, indexing, and encryption support.
Security vulnerability in GitHub Actions allowing forked repository commits to bypass workflow restrictions in CI/CD pipelines.
AgentVerse open social network platform for AI agents with community collaboration capabilities.
Tech opinion piece examining 'taste' as emerging Silicon Valley buzzword for AI product positioning.
Discussion analyzing whether AI agents resemble von Hammerstein's characterization of industrious but stupid military officers.
Headline-only post about trillion-dollar automation race with minimal content.
Tool for capping API spending per AI agent with local-only storage, supporting OpenRouter and AIHubMix platforms. Open source agent framework.
Open-source repo template for AI-assisted software development with structure from objectives through architecture decisions. Tool-agnostic design.
NEXRAD weather radar data converted to interactive 3D point clouds using auto-generated code pipeline with Python and JavaScript.
Proposal for externalizing LLM conversation context into persistent external memory to maintain alignment across sessions.
Analysis of inconsistent AI-generated UI design and how design systems enforce visual consistency in agent-produced interfaces.
Self-hosted AI research assistant for academic paper management, literature search, deadline tracking using GLM-5 with Overleaf integration.
Rook is an open-source AI assistant for Telegram with memory, voice capabilities, and plugin support.
Blog post comparing optimization of Google App Campaigns using MMP versus Firebase events as source of truth.
Jean is a development environment designed for building and managing AI agents.
MakhalReader is RSS reader using LLM to score articles 0-10 before opening, filtering noise for engineers with reading backlogs.
Collection of 63,000 AI agent skills for Claude, ChatGPT and other platforms with search and one-click integration.
Y Combinator-backed GRC platform Delve exposed for faking SOC 2 and ISO 27001 compliance reports via leaked Google Sheet.
Observations on AI adoption challenges from Bret Taylor and John Collison discussing the gap between model advances and slow client implementation.
Systemd adds age verification option to Linux following regional regulations in California, Colorado, and Brazil requiring age signals.
Agent skills package for MotionCanvas enabling AI agents to autonomously generate motion graphics videos with screenshot/export automation.
VS Code extension providing visual NPM dependency manager with package search and installation features inspired by NuGet.
Investigation of AI-generated low-quality children's educational content with factual errors spreading on video platforms.
Apple announces M5 and A19 GPU acceleration for machine learning workloads. Brief promotional announcement without technical details.
Pydantic-Deep framework extends Pydantic AI to build production deep agents with planning, file operations, task delegation, and isolated code execution.
Research team uses AI analysis of engraved limestone object from Roman Netherlands to decode ancient board game rules.
HN thread asking about current minimal hardware options for running LLMs and neural networks locally with power efficiency.
Commentary on economic disparity where AI systems use website content for training while content creators receive no compensation.
AI Team OS platform enables Claude to autonomously manage projects, execute tasks, and evolve without continuous human prompting.
OpenAI acquires Astral, company behind Python tools uv, ruff, and ty. Astral team joins OpenAI's Codex team to continue open source work.
ZBot open-source embedded AI agent runs ReAct loop on 448KB RAM microcontroller using Zephyr RTOS, connects to OpenAI APIs, controls hardware.
HN discussion sharing prompt engineering tips for Claude with emphasis on detailed planning and testing strategies for LLM-assisted development.
Practical guide on using GPT-5.4 for generating production-ready frontend designs with improved UI capabilities and image understanding.
Debian Linux 2026 election accidentally has only one candidate running for leadership position.
Brief show post title about machine learning and AI without hype with minimal content.
Title only. Likely about robust AI agents. No abstract or details available.
Supermicro co-founder charged with diverting $2.5B worth of Nvidia GPU servers to China in violation of US export controls.