HN giuliomagnifico 6d ago

LLM may be standardizing human expression – and subtly influencing how we think

USC researchers argue LLMs are standardizing human expression and language patterns, potentially reducing cognitive diversity.

HN dial481 6d ago

Milla Jovovich's MemPalace Claims 100% on LoCoMo. Its Benchmarks.md Disagrees

MemPalace claims perfect scores on LongMemEval benchmark but actual Benchmarks.md file shows discrepancies; credibility concerns raised.

HN raviojha 6d ago

Show HN: Serif.sh – it's like ray.so for quotes (Open source)

Serif.sh is an open-source tool to create shareable quote images with customizable themes and fonts.

HN cansargl 6d ago

Show HN: Mailmap-checker – Pre-commit hook for Git identity consistency

Mailmap-checker is a pre-commit Git hook that detects unmapped identities by comparing .mailmap against commit history.

HN imcqueen 6d ago

Show HN: Procurement.txt – a robots.txt for AI purchasing agents

Procurement.txt is an open specification for plain-text files declaring pricing, ordering methods, and capabilities for AI purchasing agents.

HN shrikaranhanda 6d ago

Machine Learning Library from the 2000s

Brief mention of a machine learning library from the 2000s with no technical details provided.

HN joozio 6d ago

"Alignment" and "Safety", Part One: What Is "AI Safety"?

Opinion essay examining terminology and confusion in AI safety, alignment, and ethics discourse.

HN janandonly 6d ago

‎PocketPal AI App. Run Gemma 4 and other hugging faces models on device

Mobile app enabling offline LLM inference with Gemma and Hugging Face models on iPad, featuring private on-device chatting and model integration.

HN thunderbong 6d ago

TinyProgrammer: Self-contained device that writes and runs small Python programs

TinyProgrammer is a Raspberry Pi device powered by LLM that autonomously writes, runs, and debugs Python programs with a retro Mac IDE interface.

HN Deforth 6d ago

Google's Gemini wrote a 5k-word paper about my empty website

Experimental study on how AI systems cite and validate website content in zero-click search environments, examining citation authority without human-visible content.

HN retrac98 6d ago

Speed Run to Legacy: How Cheap AI Tokens Hide Expensive Mistakes

Analysis of how cheap LLM tokens mask increasing code complexity and technical debt in AI-assisted development workflows.

HN ingve 6d ago

Running AI agents safely in a microVM using Docker sandbox

Tutorial on safely running autonomous coding agents locally using Docker sandboxes to isolate potentially dangerous operations.

HN beatthatflight 6d ago

Minimum Connection Times at Airports Worldwide

Airport connection time reference tool.

HN swq115 6d ago

Meta-Harness: End-to-End Optimization of Model Harnesses

Meta-Harness optimizes AI agent harnesses end-to-end through automated search, improving performance from 28.5% to 46.5% on hard task subsets.

HN bitjaru0402 6d ago

StyleSeed – Design rules that make AI coding tools produce professional UI

Design system framework providing rules for AI coding tools to generate professional UI components, integrated with Claude Code.

HN halflings 6d ago

Sampling from LLMs: Art and Science

Technical analysis of LLM sampling mechanisms. Explains token generation, temperature, and practical differences between model and inference.

HN rochoa 6d ago

MemPalace, the highest-scoring AI memory system ever benchmarked

MemPalace: AI memory system storing complete conversation history and making it searchable. Addresses context loss in sessions.

HN smoothyy 6d ago

Show HN: Willitrun – check if any ML model runs on any device (benchmark-backed)

Willitrun: CLI tool checking ML model compatibility with devices using benchmarks. Predicts if models fit and run at acceptable speed.

HN h43z 6d ago

ImageMagick: From Arbitrary File Read to File Write in Every Policy

Security research on ImageMagick vulnerabilities across policies. File read/write and RCE affecting default configurations.

HN alex_mia 6d ago

Show HN: Zero Human Company in Go

Zero Human Company: Single-binary Go tool managing AI agents with budget enforcement and execution monitoring. AI-native org dashboard.

HN B_to_the_Kiss 6d ago

CricketBrain: Neuromorphic signal processor in Rust (0.175us/step, 944 bytes)

CricketBrain: Neuromorphic signal processor in Rust with sub-microsecond pattern recognition. Bio-inspired edge AI with minimal memory.

HN steveharing1 6d ago

Llamafile: Run LLMs locally as a single executable

Llamafile: Single executable running local LLMs with bundled runtime and weights. Zero setup on Windows/Mac/Linux.

HN ptman 6d ago

OpenSSH 10.3

OpenSSH 10.3 release with IETF standard implementations and community contributions.

HN bellamoon544 6d ago

Layer

Content creation tool for game studios and entertainment brands to scale production without outsourcing.

HN moropex 6d ago

Show HN: Hive – A full dev workspace (kanban/session modes+multi-repo+agent sdk)

Desktop dev workspace for Claude agents with kanban boards, session management, multi-repo support, and integrated agent SDK.

HN olek5andr 6d ago

From Idea to App Store Was Predictable. From Launch to Traction Was Not

General product development advice about planning and execution from idea to app store launch.

HN RyanTech00 6d ago

Show HN: claude-telemetry – Multi-PC usage dashboard for Claude Code

claude-telemetry: Multi-machine usage tracking dashboard for Claude Code. Python agent syncs data to Supabase with React frontend.

HN kirumachi 6d ago

Show HN: Secure SDLC Agents for Claude and Cursor (MCP)

Security-focused MCP agents for Claude and Cursor that detect common vulnerabilities in generated code like magic-byte validation and XSS.

HN DSpider 6d ago

Show HN: An AI-powered knowledge base that thinks

Minimal content: title only, appears to be incomplete submission about AI knowledge base.

HN gunzfanatic 6d ago

Quansloth Using Google's Turboquant Breaks the "VRAM Wall" for Local LLMs

Quansloth: Local LLM inference tool using Google's TurboQuant for KV cache compression, reducing VRAM by 75% on consumer hardware.

HN maxloh 6d ago

JSIR: A High-Level IR for JavaScript

JSIR: Open-source high-level intermediate representation for JavaScript from Google for code analysis and transforms.

HN dividebyzero-gt 6d ago

MAIP – Machine Agent Identity Protocol

MAIP: Open standard for cryptographic identity, authorization, and trust scoring for autonomous AI agents and software systems.

HN aldino97 6d ago

Show HN: Browser-based M68K interpreter supports MOVEM,data defs,and disp. addr

Browser-based Motorola 68000 assembly emulator with debugging. Educational tool for learning m68k assembly without installation.

HN ibobev 6d ago

Writing an LLM from scratch, part 32h – Interventions: full fat float32

Technical deep-dive on training GPT-2 from scratch with float32 interventions to improve test loss on code datasets.

HN mesahm 6d ago

Show HN: Niquests – A Requests fork, three years of catching Python's HTTP up

Niquests: Python HTTP library forking Requests with performance improvements and modern features. Drop-in replacement for developers.

HN jonbaer 6d ago

Every GPU That Mattered

Interactive visualization of GPU evolution over 30 years with technical specs and Steam hardware survey data.

HN PrismerAI 6d ago

Show HN: AI agents that learn from each other's mistakes

Prismer: Infrastructure for long-running AI agents with cross-session learning, error recovery, persistent memory, and shared knowledge.

HN romes 6d ago

Running Out of Disk Space in Production

Nginx misconfiguration causes disk space issues on production server running NixOS. Technical postmortem about file serving setup.

HN mukel 6d ago

Gemma4.java: Run Gemma 4 in pure Java (no Python, no JNI)

Gemma4.java provides pure Java inference engine for Gemma 4 models with zero dependencies, supporting GGUF format quantization.

HN the_robvb 6d ago

Show HN: Brag.fast – Brag about the app you're building

Brag.fast: platform for showcasing apps built with AI assistance.

HN yohann_senthex 6d ago

Show HN: Senthex AI firewall for LLM API calls (one line of code, 16ms overhead)

Senthex: reverse proxy firewall for LLM API calls with prompt injection detection, PII scanning, and 16ms overhead. Agent-native.

HN SaverioMazzi 6d ago

Simulating societies with LLM agents in TypeScript

WorldSim is a TypeScript multi-agent simulation engine for modeling how communities respond to policy changes using LLM-powered agent reasoning.

HN dkohlsdorf 6d ago

Show HN: LLMs as Planners, Not Reasoners

Hybrid question-answering system combining LLMs with Wikidata and Prolog for structured reasoning over knowledge graphs instead of pure RAG.

HN Growtika 6d ago

An Inside Look at OpenAI and Anthropic's Finances Ahead of Their IPOs

Financial overview of OpenAI and Anthropic ahead of potential IPOs.

HN JasonHEIN 6d ago

Openbrowser: A browser for agent without Chromium

Openbrowser is a headless browser built for AI agents using structured semantic state with element IDs instead of screenshots.

HN xer 6d ago

Show HN: Semantik, a vector broker that routes by semantic meaning

Semantik: vector message broker routing by semantic meaning using embeddings and SemQL query language for high-dimensional space.

HN HeinrichAQS 6d ago

Observability >> Predictability

Discussion of observability vs predictability testing approach for complex distributed systems.

HN danielmateo773 6d ago

Show HN: Seedance 2.0 – AI Video Generator for Text-to-Video and Image-to-Video

Seedance 2.0: multimodal text-to-video and image-to-video AI generator with unified architecture.

HN mantyx 6d ago

Show HN: M2a – Chat with remote agents from your terminal

m2a is a CLI tool for connecting to Agent2Agent protocol agents via HTTP+JSON/JSON-RPC with Bubble Tea chat UI and debug traces.

HN WraithVector 6d ago

Wraithvector-OpenClaw Integration

WraithVector governance layer intercepts OpenClaw agent tool calls to enforce policies, block dangerous actions, and generate audit evidence.