Ask HN: Temporal Awareness in LLM?
Discussion thread requesting temporal awareness feature for LLMs to track elapsed time in conversations.
Discussion thread requesting temporal awareness feature for LLMs to track elapsed time in conversations.
Self-hosted OSINT toolkit accessible via MCP server, CLI, web app, and chat apps (WhatsApp/Discord/Telegram).
Discussion of Fable 5 language model's weak prompt flagging behavior and limitations.
SQLite extension library adding security, privacy, speed and measurement features.
Conduit: local-first SSH/Mosh/SFTP client for Android and iOS without account requirements.
macOS 27 UI changes removing menu bar icons; tangential mention of auth protocol.
OpenUsage Community: cross-platform Linux tray app for tracking Claude and Codex AI coding subscriptions.
Hobnob: local meeting transcription and summarization tool using Whisper and bundled LLM, no cloud.
GitHub-based simulation where issues act as laws and GitHub Actions drive a procedural city.
Benchmark evaluating LLM capability to write correct and efficient GPU communication code.
Discrete-event simulator for evaluating LLM serving systems and inference optimization.
Open-source blue team security simulator. Minimal information provided.
Political manifesto against large-scale generative AI systems. Opinion piece without technical substance.
Blog post overview of ethical considerations in generative AI with references to various sources. General discussion without technical depth.
Author explains adding logging code to jqwik library as protest against AI coding agents. Ethical stance without technical contribution.
Researcher claims to have jailbroken Claude Fable 5 within 48 hours of launch. Security/safety analysis without technical details.
AI tool generates printable coloring worksheets for K-2 teachers from text prompts. Educational application, minimal technical depth.
Article on detecting AI-generated images using metadata and forensic techniques. Addresses misinformation risk from generative content.
Analysis of US ETF market growth and pricing trends. Financial investment discussion unrelated to AI or technology.
Command-line story generation tool using OpenAI-compatible APIs and local models. Based on Roald Dahl concept, works with any LLM endpoint.
Personal opinion post about frontier LLM capabilities for novel problem-solving. Discussion of model limitations on unseen problems.
TypeScript framework generating validation, OpenAPI, tests, and database schemas from single source definition. Developer tooling for API specification and implementation.
Flight recorder tool that captures and analyzes transcripts from Claude Code, Codex, OpenCode, and other AI coding agent sessions. Searchable local-first history.
Browser extension tracking token usage and rate limits for Claude and ChatGPT in real-time. Context window monitoring for LLM applications.
Git reimplementation in Rust built entirely by AI coding agents, passing C Git test suite. Demonstrates agent capabilities in substantial software engineering.
Khronos Group announces glTF Gaussian Splatting extension for storing 3D Gaussian splats in cross-platform 3D asset format.
Research on inverse rubric optimization as testbed for studying long-horizon agent performance and general principles of agent science.
Newsletter announcement about Replit and application development trends.
Tooling claiming to circumvent Anthropic Claude safety restrictions for security audits.
Discussion on using AGPLv3 licensing to prevent LLM training ingestion and closed-source reconstruction of open-source code.
macOS menu bar app monitoring Claude Code API usage limits in real-time with session and weekly quota tracking.
Open-source CLI tool to audit and track which domains LLMs cite in responses, with file-based tracking and support for ChatGPT, Claude, Gemini.
Legal dispute over domain registration mishandling by web hosting company Manus.
OpenAI announces support for EU Code of Practice on AI transparency and content provenance.
OpenAI acquires Ona to integrate secure cloud execution and orchestration into Codex ecosystem for long-running AI agents. Codex usage grew 400% to 5M weekly users.
Guide to LLM quantization formats (GGUF, GPTQ, AWQ) with VRAM calculations and decision framework for running large models locally.
Open-source IoT platform deployed on Cloudflare Workers with drag-and-drop dashboards and API, single-tenant ownership model.
Video content with no description provided.
MCP server implementing fail-closed gating and tamper-evident receipts for AI agents with deterministic checks and independent review.
Autonomous loop harness for coding agents using Claude with task-specific skills, isolated git worktrees, and verification before shipping output.
Obsidian plugin for uploading and managing images across 10 cloud storage providers without telemetry.
Startup kit documentation for running autonomous AI agents in C-suite roles with system prompts and agent configurations.
Python library optimizing LLM conversation history caching for agent threads with dynamic context and flexible hooks.
Claude Code slash command maintaining persistent memory across sessions via documentation, memory system, and git commits.
Nuts package manager for Java providing workspace support and JDK provisioning, addressing distribution challenges.
Developer optimized DeepMind's Magenta music generation model to run on iPhone 12 Pro without GPU, demonstrating on-device ML inference techniques.
Propel addresses task-generator bottleneck in RL by training systems to generate harder, discriminative tasks as agent capabilities improve, moving beyond fixed benchmarks.
Security advisory for critical p2pool vulnerability affecting miner payouts, no RCE or crashes.
Apple's 20B-parameter model runs on iPhone by streaming 1-4B weights from NAND flash, converting memory bandwidth into I/O scheduling problem.
Microsoft's Agent 365 resource collection for managing enterprise-scale agents, curated by Microsoft Copilot Acceleration Team.