HN jen20 17d ago

Slowjson – attack on HTTP servers accepting JSON with chunked transfer encoding

Security research on HTTP slowjson DoS attack affecting PHP/ASP.NET/Java servers. Infrastructure security unrelated to AI.

HN kris_osiadacz 17d ago

GPT-5.6 Sol: ~20 US govt-approved orgs only. What about non-US businesses?

Analysis of US government restricting advanced AI model access to foreign users. Policy impact on AI market.

HN alfiedotwtf 17d ago

Ask HN: Running local LLMs? What's your model and hardware

HN discussion of local LLM models and hardware configurations. User experiences running open-source LLMs locally.

HN megamike 17d ago

It's 11:00 pm. Do you know where your AI agent is?

Essay on AI agents as autonomous programs that execute actions without human review. Definition and implications of AI agents.

HN bogdiyan 17d ago

Asian AI startups launch Mythos-like models

Chinese and Japanese AI startups launch LLM models competing with Anthropic. LLM model announcements with geopolitical context.

HN SufficientFix42 17d ago

Show HN: Aerial-autonomy-stack – open-source perception-based drone swarms

Open-source drone swarm stack combining autopilots, ROS2, and hardware-accelerated computer vision. Autonomous systems with perception-based AI.

HN speckx 17d ago

Why LLMs Will Not Have Your Next Big Idea

Personal perspective on LLM limitations for original innovation, based on years of practical experience using LLMs for coding, research, and analysis.

HN nietras 17d ago

Previewing Speccat.com – Compare CPU, APU, GPU Specifications Instantly

Web tool for comparing CPU/GPU specifications using LLMs. Mentions LLM application but limited depth.

HN mebcitto 17d ago

Open-source cloud-native Postgres platform

Open-source Postgres platform for self-hosting on Kubernetes. Not AI/ML related.

HN logn 17d ago

BlueBookOS: An LLM microkernel and language for specifying apps

BlueBookOS is an LLM microkernel and language for specifying apps; paste rules and source code into an AI model to build source-first artifacts in live chat.

HN shauryaSP 17d ago

Show HN: Nirnam – a browser-native message bus and AI agent framework for MFEs

Nirnam is a browser-native message bus and AI agent framework for micro-frontends, enabling SharedWorker-based pub/sub, request-reply, streaming, and MCP transport.

HN triska 17d ago

Kb – Prolog Knowledge Base

Kb is a local-first, hyper-relational knowledge base with content-addressable storage built as a Master's thesis prototype using Prolog and SQLite.

HN reinhardt 17d ago

Ask HN: Is there a quiet market for 'no enforced AI' dev jobs?

Discussion thread about demand for software engineering jobs that explicitly restrict or discourage AI tool usage among burnout-affected developers.

HN xiaoke-api 17d ago

XiaoKe API Gateway: PDF OCR Scrape Translate Review SummarizeXiaoKe API Gateway

XiaoKe API Gateway provides 7 micro-APIs for AI agents (PDF OCR, scrape, translate, review, summarize) with autonomous payment via x402/USDC, zero auth/KYC.

HN mehmetoguzderin 17d ago

Gnome AI Assistant Adds Image Generation Support

GNOME AI Assistant now supports image generation capabilities.

HN nathan_tarbert 17d ago

Show HN: Open Tag, the open source Claude Tag

Open Tag is an open-source Slack AI agent built on CopilotKit that reads threads, calls tools, and renders results. Self-hosted, bring your own model, no per-seat pricing.

HN aymanhs72 17d ago

Jeeves: A minimal systemd TUI written in Go for lightweight hardware

Jeeves is a keyboard-driven terminal UI for systemd written in Go, enabling quick inspection and management of system units without command-line typing.

HN KellyCriterion 17d ago

India: Factory workers told to film themselves for AI/robot training

Report on Indian garment factory workers being required to wear head-mounted cameras to capture footage for AI and robot training systems.

HN horatiucode 17d ago

Everyone Will Have an AI Coding Agent

Clawie is a packaged AI coding agent workspace with configurable LLM provider, model, and API settings, repo-mapping, and REPL-based development workflow.

HN jalopy 17d ago

Ornith-1.0: A family of open-source LLMs specialized for agentic coding

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding tasks.

HN Avenassh 17d ago

Show HN: PreFlight – A local AST background daemon to catch AI code drift

PreFlight is a local AST daemon, MCP server, and VS Code extension that prevents AI hallucination, schema drift, and broken RLS policies in real-time without authentication.

HN harpreetsingh80 17d ago

Show HN: Mcpify – Turn any REST API into an MCP server in one command

Mcpify automatically converts REST APIs into MCP servers by reading OpenAPI specifications and generating tool wrappers, eliminating manual endpoint wrapping.

HN vinhnx 17d ago

Properties of AI

Educational overview of how generative AI works: token-by-token prediction, training data limitations, context windows. Introductory content without original research.

HN bonigv 17d ago

Ask HN: How do we measure software in LLM era?

Discussion thread asking how to measure software quality and improvement in systems using LLMs given variability across metrics like accuracy, cost, context, and latency.

HN schmuhblaster 17d ago

Getting LLMs Drunk to Find Remote Linux Kernel OOB Writes (and More)

AI agent system discovered 20+ CVEs including Linux kernel OOB writes using self-orchestrating vulnerability-hunting agents. Technical analysis of LLM-based security research.

HN lureilly1 17d ago

Show HN: The TypeScript Semantic Layer for ClickHouse

Type-safe semantic layer for ClickHouse in TypeScript. Compiles to SQL, no external runtime. Enables reusable metric definitions for analytics.

HN aurenvale 17d ago

DeepSeek open-sources inference optimizations with 60–85% faster generation [pdf]

DeepSeek releases inference optimization research achieving 60-85% faster token generation. PDF technical report on optimization methods.

HN thunderbong 17d ago

What Everyone Gets Wrong About AI and Learning [video]

Video content on AI and learning misconceptions. No technical depth or accessible details provided.

HN dttdrv 18d ago

Show HN: PhoneCode: Local-First ADE Running Natively on Android

Android IDE running Alpine Linux locally via proot with Python, Node.js, and git. Uses LLM coding via models.dev with encrypted API keys.

HN thedebuglife 18d ago

Higher rate limits on the Claude API

Claude API rate limit documentation and configuration options for AWS Marketplace deployments.

HN notTechy 18d ago

How to evaluate multimodal VLMs for your video use case

Practical workflow for evaluating video VLMs using VideoDB and Langfuse. Includes open-source benchmark repo for testing VLMs on video tasks.

HN guy-sela 18d ago

Show HN: Brytlog – AI logger

AI logger using cheaper models to summarize raw logs for agent workflows, reducing processing costs and context bloat.

HN ethical 18d ago

The Calculator Discipline – AI-Assisted Disclosure Hallucinations

Analysis of AI-assisted code review generating false vulnerability reports in security bug bounties and open-source projects.

HN birdculture 18d ago

NLNet Labs LLM Policy

NLNet Labs policy restricting LLM use: requires human authorship of contributions, prohibits AI-generated code/docs. Organizational governance document.

HN grajmanu 18d ago

Gstack

Essay on AI agents enabling solo builders to ship at team scale. References Karpathy and solo open-source projects. Motivational rather than technical.

HN grajmanu 18d ago

Free-For.dev

Curated list of free developer services and SaaS offerings with free tiers. Resource for finding tools.

HN grajmanu 18d ago

Git Push No-Mistakes

Git proxy tool using AI-driven validation pipeline to prevent push errors. Runs checks in disposable worktrees and auto-opens PRs.

HN nikitafaesch 18d ago

RelayMatch | Get your idea in front of the right people in 5 minutes.

Promotional content for RelayMatch, a contact-finding service. Appears to be spam/self-promotion.

HN EvgeniyZh 18d ago

Searching for a [72,36,16] extremal code

Distributed computing project searching for extremal binary codes. Specialized mathematics, not AI/ML focused.

HN azhenley 18d ago

Tug: An IDE for AI Coding

Personal IDE project for AI-assisted coding with custom component system and middleware architecture.

HN anglerbay 18d ago

McNUFFT – Nonuniform FFT for Apple Silicon GPUs via MLX

GPU-accelerated non-uniform FFT library for Apple Silicon via MLX. Includes technical paper on precision handling and performance.

HN Lamis-A 18d ago

When a measure stops helping people see and starts teaching them to hide

AI intelligence layer architecture: software system connecting AI assistants to multiple business data sources via natural language queries with validation.

HN lucasepe 18d ago

After years of working with Go, I wrote the interview guide I wish I'd had

Interview guide for Go programming language candidates.

HN zackchew 18d ago

Show HN: OpenClaw Launch – deploy a managed OpenClaw AI agent in 30s

Research measuring whether AI models follow architecture constraints; Claude Opus violated rules 60% of the time. Empirical ML evaluation.

HN fagnerbrack 18d ago

LFM2 VL WebGPU

Essay on measurement systems in organizations and how metrics can undermine engineering judgment and care. Management philosophy.

HN toyoshi 18d ago

Show HN: An LLM that designs M5Stack hardware builds

Title only, no content. LFM2 VL WebGPU project reference unclear.

HN othmanosx 18d ago

AI writes code faster than you can review it

GitHub Copilot increased coding speed 55% but code review time unchanged; explores AI as amplifier for teams.

HN cysparrow 18d ago

Blue print to let machines think like humans

LLM application that generates hardware designs for M5Stack devices. Limited content available.

HN josefchen 18d ago

Testing 67 Models: Combining LLMs Rarely Beats the Best Single Model

Informal philosophical speculation on achieving human-like thinking in machines using current LLM technology. Unsubstantiated.

HN taubek 18d ago

Lore: Next-generation open source version control

Brief mention of Android desktop mode resolution on Razr Fold device. Hardware specs only.