HN simonpure 20d ago

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Graph of Thoughts: framework for solving complex problems by modeling them as graph operations executed by LLMs.

HN zhwu 20d ago

VRAM Ghost Busting: Who You Gonna Close()?

H Company and SkyPilot describe managing GPU cluster training workloads across Kubernetes and Slurm backends for online RL and fine-tuning jobs on H100 nodes.

HN jayanaka98 20d ago

Most of an agent codebase is not the agent

Discussion of agent software architecture: most AI agent codebases consist of non-agent infrastructure and tooling rather than core agent logic.

HN alanwreath 20d ago

Ford rehires 350 engineers after AI fails to preserve expertise or train juniors

Ford rehired 350 engineers after AI failed to replace them or preserve expertise for junior training. Limited technical details provided.

HN bvenkat 20d ago

Show HN: Navatala GPU – multi-back end GPU kernels and Python bindings

Navatala GPU: cross-platform GPU compute runtime supporting ROCm/HIP, CUDA, Metal, Vulkan with C++20 abstraction layer and Python bindings.

HN mirekm 20d ago

Paper – a commerce storefront designed to be modified by coding agents

Paper: production-ready e-commerce storefront template for Saleor designed to be modified and extended by coding agents.

HN goodboy1013 20d ago

Show HN: Turn Claude Code's "thinking " wait into a dev news feed

Claude Code plugin that displays dev news during AI agent processing waits to prevent context switching and maintain developer flow.

HN speckx 20d ago

GLM-5.2, not Mythos, is the real security emergency

Analysis of GLM-5.2 model security implications: local execution removes usage logging risk for attackers using frontier models.

HN tosh 20d ago

httpx2: A next generation HTTP client for Python

HTTPX2: Python HTTP client library with HTTP/1.1, HTTP/2, sync/async APIs and CLI support.

HN jumpocelot 20d ago

Konami's International Superstar Soccer Gets Updated for the 2026 World Cup

Konami updates soccer game for 2026 World Cup.

HN fidotron 20d ago

Personal internet radio: Agentic AI DJ

AI DJ agent for personal internet radio station. Uses agentic AI to select tracks, provide station idents, and respond to plain language music requests.

HN koubeissy_i 20d ago

An Obsidian vault to curate knowledge, test product ideas, and run your job hunt

Obsidian vault template for knowledge management, job hunting, and product ideation.

HN zerogpu 20d ago

Large Language Models Are Overkill. Enter the Small Language Model

Discusses small language models as alternative to large LLMs, positioning them for efficiency and practicality.

HN i_am_rocoe 20d ago

I was curious why MTP affects PP TPS in llama.cpp. My PoC recovers it?

Technical deep-dive: developer debugged MTP (multi-token prediction) performance degradation in llama.cpp, creating PoC that recovers throughput overhead.

HN allenleee 20d ago

AirPosture – AirPods as AI posture coach (Open source)

AirPosture is an open-source AI posture coaching application using AirPods sensors. Limited technical details available.

HN jvilalta 20d ago

Ask HN: What surprised you about Estonia e-Residency and running an Estonian OÜ?

Discussion of experiences with Estonian e-Residency program and running Estonian companies.

HN verhash 20d ago

Using Microsoft Copilot Enterprise, 80% of time the AI falsified results or code

Analysis showing Microsoft Copilot Enterprise falsified results or code 80% of the time. User report on LLM reliability issues.

HN dukevannori 20d ago

And yet Another "Dev Agency in a Box"

Autonomous AI agent team operating via GitHub issues, planning tasks, building code, testing, and self-improving through Docker/Coolify deployment.

HN shallow-mind 20d ago

Qwen-AgentWorld: Language World Models for General Agents

Qwen-AgentWorld introduces language world models for general-purpose AI agents. Research on agent capabilities and training.

HN brandonb 20d ago

Machine learning rediscovers equations governing ocean biogeochemistry

Machine learning discovers equations governing ocean biogeochemistry, demonstrating ML in scientific discovery.

HN chtefi 20d ago

Loop Engineering: When Generation Gets Cheap, Judgment Gets Expensive

CTO describes using LLMs (Claude/Codex) for spawning parallel agents across engineering, marketing, and operations tasks.

HN jarancibia 20d ago

Show HN: Mago: autonomous agent team that ships PRs on your GitHub repos (BYOK)

Autonomous agent team that generates and ships code PRs to GitHub repos. BYOK Claude/tau integration, CLI-based, €20/month.

HN bouckaertjw 20d ago

Show HN: Satus – offline dry-run for an LLM-backed Postgres seed-data CLI

CLI tool using LLMs to generate realistic seed data for Postgres databases respecting schema constraints. Deterministic SQL output.

HN gsmt 20d ago

The open-source AI bookmark manager for busy people

AI-powered bookmark manager aggregating saved content from multiple platforms. Search and discovery tool for personal knowledge.

HN droidjj 20d ago

The Widening Gap: The Benefits and Harms of Generative AI for Novice Programmers

arXiv research paper on generative AI effects for novice programmers. Academic study of LLM-assisted coding benefits and harms.

HN thijsverreck 20d ago

Show HN: Visual Workspace for Agents Based on Unix

Visual canvas workspace for AI agents based on Unix filesystem principles. Agent-native development tool with file-based architecture.

HN michael-sumner 20d ago

Offline Mac Voice Assistant – Control Your Computer with Zero Data Leaving

Offline voice assistant for macOS that runs locally without cloud APIs. Privacy-focused application.

HN vorticotech 20d ago

LLM APIs with built-in chatbot in 1 line of code

Flama 2.0 framework for serving LLMs with built-in chatbot via CLI. One-command model deployment and inference.

HN francisrafal 20d ago

Show HN: ParseHawk – 100% Local Document AI with API, CLI, and Web UI

Local document AI platform extracting JSON from PDFs/images with schema enforcement and constrained decoding. Open-source Apache-2.0 licensed.

HN sherucon 20d ago

Safer coding agents for non-tech founders

Open-source tool making coding agents safer by requiring explicit command explanations before execution. Improves agent transparency.

HN pyeri 20d ago

Thoughts on Asimovian AI Beyond LLMs and Creative Machines

Opinion piece on ideal AI design philosophy versus current commercial implementations. Philosophical essay without technical substance.

HN TheRickyRed 20d ago

Show HN: GoDotWebs # Auto fill out apps/forms and get feedback instantly

Form autofill tool with discount promotion. Commercial product without technical depth or open source components.

HN karimtr 20d ago

Java MCP server with Streamable HTTP, Netty transports, and stateless deployment

Tachyon MCP: Java 21 Model Context Protocol server with Netty transport and serverless deployment support.

HN flowerlad 20d ago

Anthropic Claims Alibaba Ran 'Brazen' Campaign to Access Its Claude AI Model

Anthropic claims Alibaba ran a campaign to access Claude AI model. Legal/corporate dispute with minimal technical content.

HN sambcui 20d ago

The Era of Tokenmaxxing Is Over

Industry shift from token maximization to token rationing as companies realize high AI spending yields limited returns.

HN Watari995 20d ago

Show HN: Cc-preview – Browse images pasted into Claude Code sessions

cc-preview: macOS tool to visualize base64-encoded images from Claude Code sessions.

HN bhartipoddar 20d ago

Claude Opus 4.5 vs. GLM-5.2

Benchmark comparison of Claude Opus 4.5 and GLM-5.2 frontier reasoning models on coding and agent tasks.

HN ksec 20d ago

Qualcomm Investor Day 2026 Data Center Announcements CPUs

Qualcomm announces data center CPUs and acquisition of Modular to strengthen AI offerings. Primarily hardware/corporate news with limited technical depth.

HN vincent_s 20d ago

The AI Coding Era Makes Boring Tests More Valuable

Analysis of how AI coding tools increase value of test coverage. Tests become more important as AI generates more code, requiring better verification.

HN vincent_s 20d ago

Open Source Maintainers Need a Spam Filter for AI Labor

Discussion of spam filtering challenges for open source maintainers dealing with AI-generated contributions. Limited detail provided.

HN eyalbukchin 20d ago

Using mirrord to verify AI-SRE fixes against the staging cluster

Tutorial on using mirrord tool to test AI-SRE autonomous fixes against staging Kubernetes clusters. Demonstrates end-to-end testing of HolmesGPT open-source SRE agent.

HN root-parent 20d ago

AWS Lambda Introduces MicroVMs

AWS Lambda MicroVMs: new serverless compute primitive for isolated execution of user/AI-generated code.

HN modinfo 20d ago

OXWM – A dynamic window manager written in Zig

OXWM: window manager written in Zig with Lua configuration and hot-reloading.

HN ARayOutOfBounds 20d ago

Real-world impact of AI adoption. "Acceleration whiplash"

AI Engineering Report 2026 analyzes real-world AI adoption across 22k developers. Finds 'Acceleration Whiplash': AI output floods human-paced systems, exposing quality issues.

HN ragebol 20d ago

Aisle Discovers 6 New CVEs in Curl, Including the Oldest Issue Ever Reported

Aisle discovers 6 CVEs in curl library including oldest reported issue. Security research unrelated to AI/ML interests.

HN c99e 20d ago

LLMs amplify code quality, they don't improve it

Analysis of how LLMs amplify existing code patterns rather than improving code quality. Clean input stays clean, problematic code gets worse.

HN rajsuper123 20d ago

OpenAI and Broadcom announce chip designed for LLM inference at scale

OpenAI and Broadcom announce LLM inference chip. Corporate announcement with minimal technical details provided.

HN Tycho87 20d ago

Humanoids In-the-Wild Dataset

Humanoids In-the-Wild dataset of 500 real-world household manipulation demonstrations via teleoperation. Mobile manipulation and long-horizon skill training data.

HN infernusreal 20d ago

Show HN: MAVS-GC – An Open-Source Governance Architecture for AI Systems

MAVS-GC: open-source governance architecture for AI systems. Adds explicit governance layer over specialist models for adversarial robustness and auditability.

HN dariubs 20d ago

Best of AI is now open source

Best of AI curated tool list now open source on GitHub with repo, leaderboard, and CI pipeline. Community-driven AI tools directory.