6d ago
Show HN: Tine – Drive Wayland Around with Agents
Tine: GNOME extension and CLI enabling AI agents to control Wayland desktop via AT-SPI2, OCR, and visual feedback.
6d ago
Show HN: Mac menu bar app for Claude Code rate limits
Native macOS menu app for monitoring Claude Code rate limits and API usage.
6d ago
Inter-1 – Omni-modal model for detecting social signals in video
Inter-1 model detects social signals in video using omni-modal approach.
6d ago
AI Agents, Contained
Title only, no content provided. Likely about AI agent safety/containment.
6d ago
Prevent Data Leakage to LLMs
Guide and methods for preventing sensitive data leakage when integrating large language models.
6d ago
Show HN: Single file Lambda Calculus' demonstrating various type system features
Lambda calculus type system implementations with no AI/ML connection; pure PL theory.
6d ago
Show HN: MetaHide – Hide Vibes in Meta.ai:)
MetaHide Chrome extension toggles visibility of Meta.ai sidebar menu items with persistent preferences.
6d ago
Lazy-loading Claude Code skills
Analysis of Claude Code's skill system: inlines all skill metadata into system prompt, suggesting need for lazy-loading optimization.
6d ago
Behind fiery attack on OpenAI's Altman, a growing divide over AI
News coverage of criticism directed at OpenAI CEO regarding AI policy differences.
6d ago
Claude Sucks
User complaint about Claude's availability and performance issues during high usage periods.
6d ago
Claude Universe: teach Claude Code to think systematically
Technique for teaching Claude Code systematic reasoning and structured thinking.
6d ago
Show HN: Hormuz Trail
Developer built Oregon Trail parody game using multiple AI models and tools. Documents approach combining Opus, GPT, Cursor, and Gemini.
6d ago
AI Coding Agents get better at functional code, but not security
Analysis of AI coding agents improving at functional correctness but lagging on security vulnerabilities.
6d ago
We built our AI agent, for analyzing CI logs
Team built an AI agent for automated CI log analysis.
6d ago
Show HN: Cush – curl your shell, an HTTP tunnel for AI agents
Cush: HTTP tunnel tool enabling AI agents to run constrained CLI commands on remote servers without VPN/SSH access.
6d ago
Show HN: Libretto – Making AI browser automations deterministic
Libretto: Open-source tool that generates deterministic browser automation scripts from AI agents instead of runtime prompts, enabling inspection and debugging.
6d ago
Ask HN: Non AI Contributor on Project Teams
Hacker News discussion about non-AI contributors on project teams and managing code quality.
6d ago
Kill the infrastructure Tax: Launch Astro in seconds
Title only, no content. Likely about deployment simplification.
6d ago
Why build on a single AI provider despite the risk? 3 AI models debated it
Discussion of risks and rationale for building applications dependent on single AI provider.
6d ago
WhatRuns extension malicious update: Full URL and AI chat exfiltration [video]
Security report: WhatRuns browser extension compromised to exfiltrate URLs and AI chat data.
6d ago
Allbirds abandons clothes, pivots to "AI compute infrastructure"
News brief about Allbirds company rebranding toward AI compute infrastructure.
6d ago
Open Source Isn't Dead. Cal.com Just Learned the Wrong Lesson
Commentary on Cal.com's decision regarding open source licensing strategy.
6d ago
AI disease-prediction models were trained on dubious data
Report on AI disease prediction models trained on poor quality or unreliable medical data.
6d ago
LeftGlove – MCP server that makes websites usable by AI agents (npx leftglove)
Open source MCP server simplifying website interaction for AI agents by filtering DOM noise and providing stable selectors.
6d ago
Show HN: L6e – Give your Agent a budget (save tokens, get smarter results)
Open source MCP server implementing token budgeting for AI agents to control costs and prevent context window bloat.
6d ago
Show HN: I built an AI music tagger for DJs, fusing metadata, audio DSP, and ML
Developer built AI-powered music tagging tool combining metadata lookup, audio DSP, and LLM processing for DJ library management.
6d ago
Show HN: SmokedMeat, like Metasploit, but for CI/CD (open-source)
Open-source red team framework for CI/CD security testing and vulnerability demonstration.
6d ago
LegendreGPT: Compressing a transformer into 15.7 MB with Legendre polynomials
LegendreGPT: transformer compression using Legendre polynomial coefficients, reduces 22 layers to 6 coefficient matrices achieving 15.7MB model size.
6d ago
Why I Am Doing This: Origin Story of Project-AI (Constitutional AI Governance)
Academic paper on constitutional framework for AI governance and enforcement mechanisms.
6d ago
Coding evals are broken. CI is green while AI code quality goes unmeasured
Technical analysis of broken AI code evaluation methods. SWE-bench marked contaminated; standard metrics fail to measure AI code quality impact.
6d ago
40% Increased Throughput 16.8% Less Energy for AI (Verified via ZKP)
Brief title about AI throughput and energy optimization improvements verified via zero-knowledge proofs.
6d ago
Show HN: Evo – parallel autoresearch experiments for Claude Code and Codex
Evo: Claude Code plugin for automated codebase optimization against metrics, built on Karpathy's autoresearch framework.
6d ago
Ask HN: Which LLM model and agentic CLI are you using for local development?
Discussion thread surveying local LLM models, hardware setups, and agentic CLI tools for development.
6d ago
Show HN: A semantic flow tool for embeddings
Experimental tool for computing and visualizing flow fields in semantic embedding spaces from trajectory data.
6d ago
I built my first AI agent (and what I got wrong)
Brief post title about building first AI agent and lessons learned.
6d ago
Show HN: Aegis – 85ns Sovereign Infrastructure Running on $100 Android Hardware
Aegis: Rust-based sovereign infrastructure achieving 85ns latency on low-cost Android hardware, targeting distributed node scaling.
6d ago
Show HN: DeepFake Detector Flags Swalwell Video as Fake
Technical analysis of deepfake detection indicators in a video using visual artifact analysis.
6d ago
Ask the Zuckbot? Meta Reportedly Building AI Clone of Mark Zuckerberg
Report that Meta is building an AI avatar of Mark Zuckerberg trained on his mannerisms and statements for employee interactions.
6d ago
A 164-parameter architecture beats a 6.5M transformer on SCAN by 94 points
HWTA: discrete routing architecture with 164 parameters outperforms 6.5M parameter transformer on SCAN compositional reasoning benchmark by 94 points.
6d ago
EvoForge: Evolutionary Harness Optimization
Title only, no content. Possibly about optimization framework.
6d ago
Five Things I Learned About Making AI Coding Agents Work
Analysis of AI coding agent behavior degradation over time, citing Meta/Harvard research on root causes beyond model limitations.
6d ago
GitHub – Heyitsnoah/Claudesidian
Open-source Obsidian vault configured for Claude Code integration, enables AI-powered note-taking and project management.
6d ago
Show HN: Compile English specs into 22 MB neural functions that run locally
ProgramAsWeights compiles English function descriptions into 22MB local neural functions with deterministic output, no API keys required.
6d ago
Reports of RAG's death have been greatly exaggerated
Technical post discussing RAG vs fine-tuning approaches for LLMs, referencing Andrej Karpathy's markdown wiki idea and introducing Atomic tool.
6d ago
Show HN: LLM inference slowdown fixed (177 experiments, +37% attention) – in 48h
Claim of 37% attention improvement in LLM inference optimization via 177 experiments. Title only, no technical details.
6d ago
Elevated Errors on Claude.ai, API, Claude Code
Status update: Claude.ai and API experiencing elevated errors. Operational status report, no technical insights.
6d ago
Mapping GPUs to LLMs (and back): A bandwidth-based estimator for local inference
Technical guide for selecting GPUs and LLM models for local inference, addressing hardware-model compatibility for cost-effective local deployment.
6d ago
Show HN: IDE like, local API client
Postchi is an IDE-like local API client built with Tauri and React for focused API development.
6d ago
Agentic Engineering Methodology – Structured AI-Assisted Dev (Karpathy, Osmani)
Methodology by Karpathy and Osmani for structured AI-assisted development using agentic approaches. Title only, no details.
6d ago
KillBench shows every major LLM is biased against Americans
Claims major LLMs show bias against Americans. Title only, no substantive content provided.