24d ago
F* file system – file search that reads SSD directly bypassing OS kernel
F* file system: CLI tool that bypasses OS kernel to search files by reading SSD directly using ~1.5k lines of C code.
24d ago
The AI Conundrum: We are living in highly subsidized, interesting times
Analysis of LLM industry economics, subsidy structures, and timeline from research to production use in programming.
24d ago
Japan chipmaking equipment suppliers report 10% drop in China sales
Newsletter digest on Japan chipmaking equipment, semiconductor pricing, and AI agent security trends.
24d ago
You're probably paying GPT prices for tasks that don't need GPT
API platform for comparing and routing requests across multiple LLM providers with unified billing and model switching.
24d ago
AI Is Taking Over Hospitals
Study comparing ChatGPT diagnostic performance against physicians in medical settings.
24d ago
I am dreading our LLM-written incident report future
Opinion piece expressing concerns about LLM-generated incident reports becoming commonplace in tech operations.
24d ago
Show HN: Lelu – catch AI agents when they're manipulated at runtime
Authorization engine detecting when AI agents are manipulated via prompt injection or anomalous behavior at runtime.
24d ago
Seeking Advice
Incomplete personal advice request about coding career direction.
24d ago
Show HN: Memory Magico – CLI based memory, wiki and deterministic sprints
Memory Magico: CLI tool for agent-focused memory, wiki, and deterministic sprint management with validation checkpoints.
24d ago
GreyFox – Free self-hosted AI proxy, token quotas, and local cache
Self-hosted AI traffic proxy with token quotas, response caching, and per-user limits via local Docker deployment.
24d ago
Ask HN: Anyone notice World Cup video feeds look like AI?
Speculation about World Cup video feeds appearing AI-generated or video game-like due to compression artifacts.
24d ago
Someone Build a OS for Claude Code
ClaudiOS: Linux distro that boots directly into Claude Code AI agent with full system access, eliminating traditional OS desktop environment.
24d ago
A cheaper and safer agentic AI workflow
Case study of agentic AI coding using GLM-5.2 model service: $0.034 cost, 3 minutes, 2 mistakes vs 1 hour human attempt with 4 mistakes.
24d ago
Tech pundit Cringely cofounds startup '2Brains Inc' to solve LLM hallucinations
Comment thread discussing Cringely's startup to address LLM hallucinations.
24d ago
Show HN: Pure Effect – Reproduce production bugs on your laptop without a DB
Developer tool enabling local reproduction of production bugs by isolating I/O from business logic without requiring production databases.
24d ago
Show HN: Vexyn – browser-only privacy tools with local AI (WebGPU)
Browser-only privacy tool suite running local AI models via WebGPU: JSON tools, Base64 encoding, QR codes, PDF/image processing without uploads.
24d ago
Two AI judges scored our agent's answer 0.85, but it never opened the file
Analysis of AI agent benchmark flaws: judge models cannot verify if agents actually accessed claimed information or checked absence claims.
24d ago
AI is a mass psychotic delusion [video]
Dismissive video commentary on AI as mass delusion. Opinion-based, no technical content.
24d ago
Show HN: A TypeScript Pokémon Crystal TUI for Agent Benchmarking
Pokémon Crystal text-based UI benchmark environment for testing AI agent capabilities in turn-based game scenarios.
24d ago
Show HN: Jacobi–IDE for Abaqus subroutine with analytical tests and AI diagnosis
Jacobi-IDE developer tool for Abaqus UMAT subroutines with AI-assisted diagnosis for computational mechanics simulation.
24d ago
AkaRouter – Flat per-call LLM API gateway (20x cheaper than Claude Max)
LLM API gateway offering Opus-equivalent models at 91% lower cost via pay-per-request pricing across frontier models.
24d ago
Show HN: Atizar-AI agents where the server runs approved actions, not the model
Agent framework where server executes pre-approved actions rather than delegating execution to language models for improved safety and control.
24d ago
Neuralwatt: Energy-based pricing for AI inference. Efficient prompts cost less
Energy-based pricing model for AI inference where prompt efficiency directly reduces computational cost to users.
24d ago
Googles specification (and tooling) for the LLM wiki
Google's Open Knowledge Format specification for universal, vendor-neutral knowledge representation as markdown with YAML. Includes agent proof-of-concept for automatic OKF bundle generation.
24d ago
Supervising AI Agents
Framework/methodology for oversight and control of autonomous AI agents. Title-only submission.
24d ago
Show HN: Askmaps.ai – Like ChatGPT with a Map
Geospatial chatbot tool combining ChatGPT-style interface with map visualization. Limited technical details.
24d ago
Is this blog written by AI?
Blog post about using AI agents for research, brainstorming, and analysis while avoiding LLM-generated text for writing.
24d ago
Show HN: I "built" Sana, a vector DB on object storage
Sana: open-source vector database on object storage built with AI assistance, prioritizing learnability over performance.
24d ago
Show HN: A C++ ALNS routing engine for LEO satellite mesh networks [video]
C++ ALNS routing engine for LEO satellite mesh networks using metaheuristics to handle mass-node failures.
24d ago
Daily_stock_analysis: LLM-powered multi-market stock analysis system
Daily_stock_analysis: open-source LLM-powered system analyzing multiple stock markets with automated reporting to messaging platforms.
24d ago
8086 Segmented Memory was a good idea
Historical analysis defending 8086 segmented memory architecture design decisions.
24d ago
I'm done with LLM-through-chat-experience
Personal philosophical rant about LLM hype and intellectual work replacement.
24d ago
Taste turns your Git history into enforceable coding judgment
Tool auto-learns coding style from git history to compress AI agent context 97% using Taste patterns.
24d ago
Brain the Size of a Planet: Are LLMs Thonking Too Hard?
Study comparing reasoning effort across LLM models (Claude, GPT) for security triage with different context windows.
24d ago
Backporting bug fixes is dead, Project Valkey now sends in the bots
Project Valkey using automated bots for backporting bug fixes instead of manual effort.
24d ago
Show HN: Teach your kids absolute (perfect) pitch
Mobile app for teaching children absolute pitch recognition using chord identification.
24d ago
Neosolve – SolveSpace fork with OpenCASCADE CAD kernel
SolveSpace fork integrating OpenCASCADE CAD kernel for parametric 2D/3D modeling.
24d ago
Tokoscope – Automatic LLM token compression and cost monitoring in 2 lines
Tool for automatic LLM token compression and cost monitoring. Developer tool for LLM applications.
24d ago
Show HN: An AI video prompt cookbook for image-to-video workflows
Practical guide with prompt patterns for image-to-video and text-to-video workflows. Resource for creators using generative AI tools.
24d ago
Show HN: AdvertBench, ranking the ability of LLMs to create image ads
Benchmark comparing LLM ability to create image ads using sandboxed tool access. Evaluates AI agents' tool use and reasoning capabilities.
24d ago
How LLMs Distort Our Written Language
Research on how LLMs affect written language patterns. Authors include machine learning researchers studying language model effects.
24d ago
Show HN: Local LLM Hardware Calculator
Calculator tool showing memory requirements for running local LLMs with different quantization levels and context lengths.
24d ago
Shall We? – A pre-engineering sanity check for AI-era feature bloat
Developer tool implementing Agent Skills open standard for evaluating feature ideas before building. Compatible with multiple AI coding agents.
24d ago
Cagebase - Chromium fork that spoofs fingerprints from a JSON profile
Chromium fork that spoofs browser fingerprints from JSON configs for bot automation and anti-detection.
24d ago
The open-source Agent Communication Infrastructure
Open-source infrastructure for conversational agent communication, enabling interactive multi-turn engagement rather than one-way notifications.
24d ago
Agent Privacy
Technical analysis of privacy control mechanisms in AI agent systems. Discusses practical privacy architecture for agent harnesses.
24d ago
Canyon Predict – road bike prototype with AI edge computing [video]
Canyon Predict is a road bike prototype with AI edge computing capabilities.
24d ago
Nvidia adopts OpenBAO, open source fork of HashiCorp's Vault
Nvidia adopts OpenBao, an open source fork of HashiCorp's Vault for secrets management.
24d ago
Show HN: Didon – AI workday reports for productivity analysis
Didon is an AI time tracker that captures periodic screenshots and generates work logs summarized into daily productivity reports.
24d ago
Brands using AI-generated influencers to promote products on social media
Investigation of brands using AI-generated influencers on social media without disclosure. Commentary on AI-generated content and transparency.