LB blog.orhun.dev by orhun 15d ago

Write less code, be more responsible

Opinion essay on AI-assisted programming: discusses benefits and drawbacks of LLM-aided coding, vibe coding culture, and responsible development practices.

HN thunderbong 15d ago

Tabularis: A lightweight, cross-platform database client. Hackable with pkugins

Tabularis: cross-platform database client built with Tauri/React. Originally developed as AI-assisted agent experiment for tool acceleration.

HN enha 15d ago

Give Your Agent a Canvas, Not Just a Chatbox

Create0 API allows agents to build workflows with multi-modal inputs (text, image, audio, video) through visual canvas interface with inspection and review.

HN alecco 15d ago

The Great GPU Shortage: H100 Rental Prices Up 40%

Market analysis: GPU shortage driven by Claude 4.6 Opus, open models, and capital raises. H100 rental prices up 40%.

HN Aiyo28 15d ago

AIYO Wisper – Local voice-to-text for macOS (WhisperKit, open source)

AIYO Wisper: open-source local voice-to-text for macOS using WhisperKit. Enables offline speech recognition without external dependencies.

HN rcron 15d ago

Show HN: LSM Trees: MemTable, Compaction, and the Amplification Triangle [video]

Video about LSM tree data structures covering MemTable, compaction, and write amplification.

HN tgnk2341 15d ago

GazeFollow from Scratch

Implementation of GazeFollow gaze detection model from NeurIPS 2015 paper using MediaPipe face detection.

HN eterer 15d ago

I built a skill manager for AI agents. The agents install the skills themselves

CLI tool for managing and distributing reusable skills across AI agent projects with GitHub integration.

HN Quynah 15d ago

I built a programming language in 6 days without writing a single line of code

Programming language built via AI without manual coding, designed for human-AI collaboration with Claude and GPT integrations.

HN abe94 15d ago

The hottest Apple product isn't what you think

Apple device setup for autonomous AI assistant workflows handling browsing, account management, and task automation.

HN hoangnnguyen 15d ago

My AI workflow evolved from prompts to a near-autonomous workflow

Evolution of AI coding workflow from prompt-based to autonomous context-aware workflows with automatic verification.

HN sucid 15d ago

IPFS Bot AI Agent Content

Minimal post title about IPFS Bot AI Agent with no content.

HN ai_psychosis 15d ago

Abundance for All – Not Just the Few

Manifesto and directory of open alternatives to proprietary systems addressing artificial scarcity.

HN JDaily 15d ago

Session-roam – Resume Claude Code conversations from any machine via Syncthing

Session-roam: P2P tool using Syncthing to sync Claude Code conversations across machines without cloud infrastructure.

HN FuzjaJadrowa 15d ago

Pulsar – Lightweight cross-platform GUI for FFmpeg and yt-dlp, built with Tauri

Pulsar: cross-platform GUI for FFmpeg and yt-dlp built with Tauri. Open source media management tool.

HN shauntrennery 15d ago

Is Numble the first AI-proof game?

Analysis of Numble daily puzzle that defeats LLMs better than Wordle. Explores what makes puzzles AI-resistant.

HN vibecoder21 15d ago

I collected startup ideas. It changed how I think about ideas completely

Personal essay about collecting startup ideas rather than obsessing over single concepts.

HN leonidas1712 15d ago

A3: Kubernetes for autonomous AI agent fleets

A3: Kubernetes-based platform for autonomous AI agent fleets at SAP Labs Singapore. Handles code, research, slides, patents, audits with task distribution and execution planning.

HN georgestrakhov 15d ago

Neural Computer

Research essay on whether AI can function as a computer and self-optimize its own execution.

HN markfront 15d ago

Show HN: RelayFreeLLM — Free AI Gateway with Auto-Failover (Updates)

RelayFreeLLM: open-source gateway aggregating free LLM APIs (Gemini, Groq, Mistral, Cerebras, Ollama) with automatic failover and OpenAI-compatible endpoint.

HN aatel-license 15d ago

Code Democracy the Big Lie

Opinion piece on whether AI coding tools like Claude Code democratize software development.

HN spaccy05 15d ago

Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs

Provepy: Python decorator using LLMs and Lean for formal code verification. Makes formal methods accessible via English claims.

HN datalater 15d ago

Crawl Code – because prompting was a text adventure

Crawl Code: Dungeon crawler game interface for Ollama LLM interactions, providing gamified prompting experience.

HN anitial 15d ago

Hindsight – A design spec for self-improving LLM agents

Hindsight: Design specification framework enabling LLM agents to learn from mistakes across sessions and internalize lessons into permanent behavior.

HN pdappollonio 15d ago

Show HN: Dux, a TUI Agent Multiplexer

Dux: TUI multiplexer for running multiple AI agents on same codebase via git worktrees, supporting Claude and other agent backends.

HN vinniefalco 15d ago

Brief: Bitcoin Core Governance Analysis

Analysis of Bitcoin Core governance arguing the project has stalled despite surface-level activity metrics.

HN haoliangyu 15d ago

Cmdgraph – Document any structural CLI for humans and agents

CLI documentation tool that recursively introspects help commands and exports structured data (JSON, Markdown, HTML) for human and AI agent consumption.

HN matt_d 15d ago

Optimization of 32-bit Unsigned Division by Constants on 64-bit Targets

arXiv framework announcement for developing features; incomplete content about division optimization research.

HN mercat 15d ago

Your next 10 hires won't be human

Multica: Open-source managed agents platform converting coding agents into autonomous teammates that handle task assignment, progress tracking, and issue resolution.

HN lablnet 15d ago

Show HN: HyperFlow – A self-improving agent framework built on LangGraph

HyperFlow is self-improving agent framework built on LangGraph. MetaAgent automatically optimizes TaskAgent performance through feedback loops.

HN kerng 15d ago

The AI-Assisted Breach of Mexico's Government Infrastructure [pdf]

PDF document about AI-assisted breach of Mexico's government infrastructure. Minimal content provided.

HN zach22 15d ago

Show HN: Lmscan – Detect AI text and fingerprint which LLM wrote it (zero deps)

Lmscan detects AI-generated text and identifies source LLM using statistical features. Open-source, offline, zero dependencies.

HN agiacalone 15d ago

Bring Back Buddy

Community response to removal of 'buddy' feature from Claude Code v2.1.97. No official changelog provided.

HN ValentineC 15d ago

Enforcing new limits and retiring Opus 4.6 Fast from Copilot Pro+

GitHub Copilot Pro+ enforcing usage limits and retiring Opus 4.6 Fast due to infrastructure strain from high concurrency patterns.

HN xlayn 15d ago

AMD GPU LLM Performance Testing

Performance benchmarking data for AMD GPUs running LLM inference. Tests actual hardware performance against theoretical specifications.

HN caihongxu 15d ago

Show HN: Palmier – Dispatch and schedule AI agents from your phone

Palmier app schedules and monitors AI agents from phone. Runs agents locally on user's machine without cloud dependency.

HN Meeeeeep 15d ago

We open sourced KubeezCut, a free browser based editor integrated with Kubeez

KubeezCut is client-side video editor using WebGPU and WebCodecs. Runs entirely in browser without backend or uploads.

HN iLemming 15d ago

Show HN: I forced Claude to play Tetris in Emacs

Developer stress-tests Claude with Emacs Tetris via custom elisp-eval MCP tool. Demonstrates LLM-driven REPL integration with persistent state across calls.

HN teleforce 15d ago

RAG 40x faster using binary quantization (2024)

Brief reference to binary quantization technique for faster RAG systems. Lacks technical details or implementation specifics.

HN festafin 15d ago

Hormuz, an MCP-first forecasting engine for reproducible modeling

Hormuz MCP-first forecasting engine for hydrocarbon-nitrogen-water modeling. Reproducible research stack with public MCP endpoint.

HN knivets 15d ago

Anthropic Mythos 0-days replicated with GPT5.4

Brief reference to Anthropic security vulnerabilities replicated in GPT5.4. Insufficient detail provided.

HN askalf 15d ago

Dario – use your Claude Max subscription as an API (no API key needed)

Dario tool converts Claude subscription into local API endpoint compatible with multiple frameworks. Supports all Claude models with native billing.

HN visionscaper 15d ago

Show HN: Collabmem – the memory system for long-term collaboration with AI

Open-source memory system for persistent human-AI collaboration over extended periods. Simple installation via MCP for long-term Claude interactions.

HN dividedcomet 15d ago

Open Source LLM Comparison – Is Opus Cooked?

Benchmark comparison of open-weight LLM models tested on identical prompts with cost and capability metrics. Tests latest frontier models on real-world tasks.

HN samchon-github 15d ago

Show HN: Function Calling Harness: From 6.75% to 100% (Qwen Meetup Presentation)

Function calling success rates for LLMs improved from 6.75% to 100% using structured output techniques. References EMNLP 2025 and ICLR 2025 benchmarks on nested tool calls and constrained decoding.

HN pabs3 15d ago

AI Code Is Hollowing Out Open Source, and Maintainers Are Looking the Other Way

Analysis of LLM-generated code integrated into open source projects and copyright/licensing implications for project sustainability.

HN thunderbong 15d ago

Daily You: A Personal Diary

Personal diary app with mood tracking and journaling features. Open-source but unrelated to AI/ML interests.

HN zeulewan 15d ago

Use Claude Max subscription with OpenClaw again

Tool to integrate Claude Max subscription with OpenClaw framework, bypassing Anthropic detection triggers.

HN tank-34 15d ago

Yet another BFF toolkit for Python

Python library for composing nested APIs declaratively with auto-batching, DataLoader pattern, and GraphQL generation.

HN Wuzu 15d ago

AI Agent Proxy to help reduce token usage (Anthropic Only)

Proxy system for Anthropic Claude that reduces token usage for AI agents.