HN mbeissinger 5d ago

Meta-Harness: automated search over task-specific model harnesses

Framework for automated search and optimization of task-specific model harnesses to improve LLM performance and efficiency.

HN kodjima33 5d ago

Show HN: Omi – watches your screen, hears conversations, tells you what to do

Desktop application that monitors screen activity and conversations to provide AI-powered proactive advice using Claude.

HN GaryBluto 5d ago

Customers revolt as GitHub Copilot 'fixes' rate limits

GitHub Copilot customers face rate limiting due to high usage patterns and a token counting bug affecting the pricing model.

HN gpjt 5d ago

LLM from scratch, part 32k – Interventions: gradient accumulation

Technical deep-dive on training GPT-2-style LLM from scratch, documenting gradient accumulation interventions and their effects on model loss.

HN hmokiguess 5d ago

Apple is sending Siri Engineers to an AI Coding Bootcamp

Apple is sending Siri engineers to AI coding bootcamp ahead of expected Siri upgrades at WWDC.

HN wkallan 5d ago

Tmux-Kanban – a web board for managing real tmux sessions

Web-based kanban board for managing multiple tmux terminal sessions, designed for AI agents and dev servers.

HN sethbannon 5d ago

Wafer maximizes intelligence per watt by optimizing kernals

Wafer raised $4M seed funding to build AI that optimizes AI infrastructure kernels for intelligence-per-watt efficiency.

HN gmays 5d ago

The AI Labs Have a $7 Doritos Problem

Opinion piece introducing AI-generated author 'Cici' for content to cash transformation analysis, uses Doritos/PepsiCo as example.

HN haragx 5d ago

Coding agent methodology built from tool failure, not theory

Methodology for building coding agents emphasizing tool failure analysis over theoretical approaches.

HN subw00f 5d ago

Ask HN: Are your product managers sending PRs?

Discussion thread about product managers writing pull requests and code quality concerns.

HN adinhitlore 5d ago

Ask HN: How far will the neo-Luddites go in their attempts to stop AI progress?

Discussion about potential anti-AI activism and violence, speculative and off-topic.

HN anupsing_ai 5d ago

Show HN: AI support chatbot with RAG and citations – one back end file, no infra

RAG-based support chatbot backend implemented in single JS file using Next.js, OnCell, and OpenRouter with citation capability.

HN CPLX 5d ago

Ask HN: What are you using in 2026 for mobile access to terminal?

Discussion thread asking developers about mobile terminal access tools for remote sessions with Claude Code.

HN randycupertino 5d ago

FDA to weigh easing limits on unproven peptides favored by RFK Jr

FDA regulatory article about peptide limits unrelated to AI/tech.

HN lrobinovitch 5d ago

Show HN: Jeeves – TUI for browsing and resuming AI agent sessions

Jeeves is a terminal UI for searching, previewing, and resuming AI agent sessions across Claude and Codex with framework integrations.

HN 01-_- 5d ago

EU threatens to force Meta to restore WhatsApp full access for rival AI chatbots

EU regulators threaten to force Meta to give rival AI chatbots access to WhatsApp, challenging Meta's access fees.

HN rolandpg 5d ago

Show HN: ZettelForge – Agentic memory for cyber threat intelligence

Agentic memory system for cyber threat intelligence with entity extraction, knowledge graphs, STIX ontology. Offline, no cloud required.

HN dnosoz 5d ago

Drarpa – CDC sync engine with exactly-once delivery and saga orchestration (Go)

Production CDC sync engine in Go with exactly-once delivery, saga orchestration, schema evolution, and PII masking.

HN mmilovanovic87 5d ago

Show HN: I built a browser idle game about training AI models

Browser idle game about running AI research lab. Teaches model training concepts: overfitting, compute tradeoffs, loss curves. React-based.

HN AutoplayAI 5d ago

SDK to make any chatbot proactive real-time

SDK enabling proactive real-time chatbot functionality.

HN AlexBThomsen 5d ago

Show HN: I Made a TradingView Alternative (Local and LLM) [video]

Local LLM-based TradingView alternative with video demo.

HN tosh 5d ago

Google Launches Native Gemini AI App for Mac

Google launches native Gemini AI application for macOS.

HN YoungGato 5d ago

I wrote a open source iMessage for your AI agents

Open source messaging platform for AI agents. Chat with agents locally and across VPS. MIT licensed.

HN gmatt 5d ago

Node.js bindings for Nvidia cuVS > GPU-accelerated vector search

Open-source Node.js bindings for NVIDIA cuVS enabling GPU-accelerated vector search and clustering on Linux with NVIDIA GPUs.

HN PaulHoule 5d ago

A Survey of Workflow Optimization for LLM Agents

ArXiv survey paper on workflow optimization techniques for LLM agents, covering methods to improve agent efficiency and performance.

HN Bender 5d ago

Tesla 'Full Self-Driving' crashed through railroad gate seconds before train

News article about Tesla Full Self-Driving incident at railroad crossing.

HN mearnest 5d ago

I made Agentation for vanilla JavaScript

Agentation for vanilla JavaScript: zero-dependency visual annotation tool enabling AI agents to understand and interact with web elements.

HN moelf 5d ago

Jane Street Signs $6B AI Cloud Agreement with CoreWeave

Jane Street commits $6B to CoreWeave's AI cloud platform for GPU compute access across multiple facilities.

HN asqpl 5d ago

Show HN: EmbedIQ – Claude Code Compliance Config for HIPAA/PCI-DSS/SOC2

EmbedIQ: Claude Code configuration wizard that generates production-ready environments tailored to compliance requirements like HIPAA/PCI-DSS.

HN roody_wurlitzer 5d ago

AI papers published in 2026 worth reading

Curated list of AI research papers from 2026 with commentary and summaries.

HN Bender 5d ago

Agents hooked into GitHub can steal creds

Security issue: AI agents integrated with GitHub repositories can potentially steal credentials.

HN ironmagma 5d ago

Show HN: Monadic Networking Library for Go

Go networking library using monadic programming for abstracting statefulness to simplify testing and logic separation.

HN phillip3655 5d ago

Claude Code now has chat

Terminal-based peer-to-peer chat for Claude Code users using distributed hash tables, no server or signup required.

HN paulpfe 5d ago

Unified MCP Server for Jira and Confluence Server/DC Behind Citrix NetScaler SSO

MCP server for Jira and Confluence Server/DC behind Citrix NetScaler SSO, using Playwright and personal access tokens for authentication.

HN embedding-shape 5d ago

HuggingFace launches pre-compiled machine learning kernels repository

HuggingFace releases pre-compiled, hardware-optimized ML kernels repository achieving 1.7-2.5x PyTorch speedups.

HN lucas_vieira 5d ago

Show HN: Fakecloud – Free, open-source AWS emulator

Fakecloud: free open-source local AWS emulator for integration testing and development, alternative to LocalStack after it went proprietary.

HN JackChen_me 5d ago

Show HN: Multi-Agent Orchestration on Top of Vercel AI SDK (TypeScript, Next.js)

Multi-agent orchestration framework built on Vercel AI SDK for TypeScript/Next.js applications.

HN manish198903 5d ago

Agents Can Act.Only You Should Authorize

Nametag protocol for AI agents to request human authorization before consequential actions with identity verification via deepfake detection.

HN Elgoghel 5d ago

Attention IS NOT all u need

HWTA: new discrete routing architecture without softmax attention beats transformers on compositional reasoning benchmarks.

HN matryer 5d ago

Show HN: Hatch: customise agents once, generate all the files

Hatch: tool to write agent configuration once and generate files for Claude Code, OpenAI, GitHub Copilot, Cursor, and other coding agents.

HN edwin 5d ago

The Security Decisions Claude Code and Codex Make

Research comparing security defaults in Claude Code vs. Codex across auth, uploads, search, webhooks.

HN steveharing1 5d ago

Moss-TTS-Nano: Real-Time Voice AI on CPU (Open-Source TTS Stack)

Open-source 100M parameter TTS model runs on CPU with competitive quality vs. Gemini/ElevenLabs.

HN siddhant-jain 5d ago

Ask HN : Vibe coders: does AI keep breaking your auth and webhooks?

Developer experience report: AI IDEs breaking authentication and webhook logic in production code.

HN Punyakrit 5d ago

Ask HN: What do founders want from a one person dev studio?

Discussion about freelance dev studio business services.

HN pranabsarkar 5d ago

Show HN: Tier – Adaptive tool routing that makes small LLMs 10pt more accurate

Tool routing system improves small LLM accuracy by 10 points via adaptive selection.

HN chronolitus 5d ago

Bot-AGI-1 – a robotics benchmark for VLMs

Robotics benchmark for evaluating VLM capabilities on physical control tasks; independent evaluation.

HN gmays 5d ago

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts

ICLR 2026 workshop paper on training data pruning techniques to improve LLM factual memorization and reduce hallucinations.

HN razvan_maftei 5d ago

Show HN: Agentfab – A Distributed Agentic Platform

Agentfab: distributed platform for AI agents featuring task decomposition, multi-agent orchestration, and self-curating memory systems.

HN CrankyBear 5d ago

'Handing out the blueprint to a bank vault' Why AI led Cal to drop open source

UC Berkeley drops open-source AI model citing security risks compared to proprietary alternatives.

HN fredmendoza 5d ago

CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous

Benchmark test showing Gemma 2B CPU model achieved comparable MT-Bench scores to GPT-3.5 Turbo with analysis of failure patterns.