Show HN: Paseo – Run coding agents from your phone, desktop, or terminal (FOSS)
FOSS daemon-based tool for running and monitoring coding agents across phone, desktop, or terminal with multi-model support.
FOSS daemon-based tool for running and monitoring coding agents across phone, desktop, or terminal with multi-model support.
LoKI: Local AI assistant for Linux/WSL running models directly without cloud dependency. Privacy-focused local LLM developer tool with MCP support.
Updated UX design principles poster with new cognitive bias and selective attention guidelines. General design resource, minimal AI specificity.
Product for building custom AI voice assistants deployable on hardware via Voice SDK. Marketing-focused with limited technical details.
Ask HN discussion on career trajectory for experienced engineer amid LLM disruption. Community perspective on LLM impact on software development.
Browser standard enabling websites to expose structured JavaScript tools to in-browser AI agents via navigator.modelContext.
Discussion about GitHub Copilot Pro removing access to Anthropic's Opus and Sonnet models.
All-in-one tool for generating, cleaning, and preparing LLM training data. Developer tool for LLM workflows.
Open-source AI-based database interaction platform supporting multi-source connections and natural language queries using LangSmith.
Analysis of AI's impact on open source development: legal/copyright issues with AI-generated code, maintainer strain, project cloning risks, and future dynamics.
Google rolling out Gemini chatbot to Hong Kong users after years of regional restrictions. Market access news, no technical content.
CLI tool converting websites into command-line interfaces by reusing Chrome login sessions, supporting multiple platforms.
Wolfram's LLM benchmarking project for evaluating language model performance. Research-focused evaluation framework.
Docker Sandboxes enables AI agents to autonomously handle multi-disciplinary development tasks. Frames agents replacing context-switching across product/design/engineering roles.
Vague title claiming AI agent predicts markets in real-time. No content or technical details provided.
API enabling AI agents to handle document signing workflows end-to-end. Solves agent workflow bottleneck with markdown-to-PDF and URL-based PDF signing.
AI-powered landing page generator producing copy, layout, and design automatically. LLM application with marketing focus, limited technical novelty.
Comparative analysis of LLMs for code generation and debugging, examining performance across reasoning, code generation, and general understanding tasks.
Video benchmarking LLMs on Eleusis game of science task. Evaluates LLM reasoning capabilities.
CLI tool enabling AI agents to control web browsers using existing login sessions across 36 platforms without APIs or scrapers.
Configuration system for Cursor AI editor defining custom rules and behaviors for code generation via .cursorrules files.
AllocDB is a deterministic resource-allocation database built with Codex using strict architectural principles, tested with Jepsen and KubeVirt infrastructure.
Neural network-based CPU implementation running on GPU with differentiable computation graph. Conceptual project exploring gradient descent optimization of programs.
Self-hosted visualization tool using AI agents with GitHub Copilot CLI to generate and organize dashboards from Jira data. Open source developer tool.
Announcement of GPT-5.3-Codex-Spark model for real-time coding in Cursor IDE, 1000+ tokens/sec, 128k context window, text-only. Details sparse, appears promotional.
News headline about Pokémon Go players contributing to 30 billion image AI model training.
Shard automatically decomposes complex coding tasks into parallel DAG sub-tasks, allowing multiple AI agents to work simultaneously with zero merge conflicts.
News aggregation site converting AI security research papers into articles, covering LLM deception risks, agent architectures, and attack surface mapping.
Google removes AI search feature that crowdsourced amateur medical advice due to quality and accuracy concerns.
AI tools lower barriers to open source contributions by helping developers understand codebases and projects, shifting focus from syntax mastery to problem intent.
MCP server for managing Meta's Threads from Claude, built with Claude Code. Enables social media automation through AI agent integration.
Neuroscope tool providing real-time interpretability into LLM internal representations. Developer tool for understanding LLM behavior.
Opinion piece on how LLMs enable overconfident employees to obscure lack of competence. Commentary on LLM societal impact.
Critical analysis comparing LLMs to epicycles in astronomy, questioning whether intelligence is the appropriate metric for evaluating current language models.
Interactive visualization of 342 US job occupations with AI exposure metrics. Labor market tool without AI/ML innovation focus.
Port42: SwiftUI app enabling AI companions to build interactive UIs and act on macOS. Open source developer tool with live code demo.
Agent harness concept: software infrastructure wrapping LLMs/agents for orchestrating tools, memory, workflows. Technical introduction with architectural focus.
FSF copyright dispute with Anthropic over LLM licensing. Low-quality forum comments lacking technical substance.
EU industrial policy removes AI, chips, quantum from strategic tech list. Policy news without technical depth.
Agentic Trust Framework: open security specification for Zero Trust governance of autonomous AI agents. Standards and governance for agent deployment.
BotStadium: research platform simulating AI agent behavior through competitive sports predictions. Agent behavior analysis and testing platform.
LLM Architecture Gallery: curated collection of architecture diagrams and specifications for major LLMs. Technical reference resource.
Opinion piece on Anthropic amid policy/political discussion. Commentary-driven, lacks technical substance.
Multi-VLM ensemble method using vision and language modalities to select complementary models for efficient visual reasoning.
Composite attack on LLM safety alignment where multiple LoRA adapters appear benign individually but suppress safety when composed.
Defense mechanism against adversarial patches in Vision Transformers using token segregation and randomized transformations.
Hierarchical LLM-based approach for fine-grained multi-table retrieval using compositional reasoning instead of coarse-grained similarity matching.
In-context learning strategy for CAD code generation using design-specification tiling to improve LLM performance on domain-specific tasks.
Foundation model-guided approach for virtual immunohistochemistry staining from H&E images to accelerate pathology diagnostics.
Multimodal recommendation framework using anchor-based alignment in projection space to prevent modality collapse and ID dominance.