AI News HubLIVE

Today's must-reads

Models

Suno snatched millions of songs from YouTube, Genius, and Deezer

In a hacking incident, AI music generator Suno's training data was exposed, revealing it scraped millions of songs and lyrics from YouTube Music, Deezer, and Genius. This supports copyright infringement lawsuits against Suno, which admits scraping but claims fair use. Customer information was also accessed, but Suno says the breach was contained and no sensitive data was compromised.

  • Leaked data shows Suno scraped millions of songs from YouTube Music, Deezer, and Genius.
  • Suno faces multiple copyright lawsuits; it admits scraping but defends as fair use.
In-site article

RL post-training on 14 Macs across 4 countries

A research team successfully used 14 Macs spread across four countries (including a personal MacBook) for reinforcement learning post-training, achieving a held-out pass@1 improvement from 29% to 63% on PaperSearchQA. The system employs PULSE weight synchronization to compress 9GB updates to ~90MB, and an asynchronous star topology with all communication via object storage—no dedicated networking required. This is the first RL post-training run using only consumer Macs for rollout generation.

  • 14 Macs across 4 countries connected via ordinary internet completed RL post-training; rollouts generated on Macs, training on a B200.
  • PULSE compresses 9GB weight sync to ~90MB, making home internet as fast as datacenter.
In-site article
Agents

What building Shippy taught us about building agents

Shippy is a maritime AI agent built for high-stakes decisions, where the wrong answer has real impacts. The article covers its architecture—soul, skills, config—and key design decisions like using a deterministic CLI for API access, sandboxed hosting for user isolation, and a custom evaluation system that scores the whole agent against live data. Lessons learned and future plans are also discussed.

  • Shippy’s architecture consists of a soul (system prompt), skills (Markdown files), and config, enabling versioned and auditable deployments.
  • A dedicated CLI abstracts complex API calls, reducing errors and ensuring predictable tool use.
In-site article

Model Routing Is Simple. Until It Isn’t.

Model routing in AI agents is more complex than it seems. It is not a classification problem but a systems optimization problem involving cost, complexity, and latency. The article shares three key challenges and explains IBM Research's optimization-based approach.

  • Actual cost depends on caching behavior, not just model pricing.
  • Task complexity is often invisible at routing time, and routers must balance multiple objectives.
In-site article

New Mac malware masquerades as Apple's crash reporter: 3 ways to dodge the threat

CrashStealer malware targets macOS users by disguising as Apple's crash reporter, stealing data, passwords, and crypto wallets. Learn how it works and three habits to stay safe.

  • CrashStealer masquerades as Apple's crash reporter (CrashReporter.dmg) and uses a signed, notarized dropper to bypass Gatekeeper.
  • It attempts to unlock the keychain, then steals credentials from password managers, browsers, and cryptocurrency wallets, exfiltrating them encrypted.
In-site article

American AI is expensive. Some startups are turning to cheap Chinese models

As AI becomes one of the fastest-growing expenses for US businesses, some startups are switching to cheaper Chinese AI models to cut costs. Despite being behind in capabilities, Chinese models offer cost advantages and open-source availability.

  • Lindy.ai saved millions by switching from Anthropic to DeepSeek-V4, which is 10x cheaper. Chinese models dominate open-source AI.
  • Companies like Uber, Airbnb, and Perplexity have explored or used Chinese models to manage costs.
In-site article

New in Fleet: Deploy AI agents to Slack in one click

Build custom AI agents in Fleet without code, then deploy them to Slack in one click. Give agents custom identities, use them in channels and threads, and keep work moving where your team already collaborates.

  • Fleet allows building specialized AI agents using natural language, no coding required.
  • Agents can be deployed to Slack with one click and have their own identity.
In-site article

Show HN: OtoDock — run Claude Code and Codex as a team of agents on your server

OtoDock is a self-hosted AI agent platform that runs Claude Code and Codex as a team of agents on your own infrastructure. It features a live dashboard, security sandbox, multi-agent meetings, automation scheduling, document generation, and supports consumer subscriptions, API keys, or local models. Licensed under the Functional Source License (FSL-1.1-Apache-2.0), with one-click Docker deployment.

  • Self-hosted AI agent platform powered by Claude Code and Codex engines, enabling team collaboration
  • Each agent runs in an isolated kernel sandbox with default network isolation and granular access control
In-site article
Tools

Show HN: Painterly – Turn pictures into digital paintings without generative AI

Painterly is a desktop app that uses a greedy algorithm with random brush strokes to turn images into digital paintings, without any generative AI. It paints strokes individually, taking minutes to hours for high-quality results.

  • Painterly uses a greedy algorithm and random brush strokes to paint
  • No generative AI; each stroke is painted individually
In-site article
Startups

OpenAI's first branded hardware is a light-up keyboard?

OpenAI launches its first branded hardware, a light-up keyboard called Codex Micro, in partnership with Work Louder. The limited-run device features OpenAI branding and highlights the company's ambitions to expand beyond software.

  • OpenAI unveils first branded hardware: Codex Micro light-up keyboard
  • Split-apart design allows keyboard parts to form a sandwich shape
In-site article
Other updates (3)
Agents

What happens when your VPN meets 200 AI agents

Legacy VPNs fail to provide secure access for AI agents. Enterprises need unified identity-based networking and privileged access management to support both human and agent workloads. Tailscale experts will discuss solutions in a free webinar on July 28, 2026.

  • Traditional VPNs and human-centric ZTNA/PAM tools are inadequate for AI agents
  • A unified architecture with consistent policies for humans and agents is needed
In-site article

Show HN: Mindlas – catch your coding agent drifting before the bad code lands

Mindlas is an open-source tool that uses deterministic gauges to monitor AI coding sessions for context deterioration, verification debt, change blast radius, and tool failure loops, providing concrete corrections before problems compound, all running locally without network calls.

  • Mindlas detects four known deterioration causes in coding sessions using deterministic gauges, with no model or network calls.
  • Four corrective actions (Context Repair, Verify Gate, Patch Splitter, Loop Stop) each record before/after effects.
In-site article

OpenAI finally launches hardware… for Codex

OpenAI has partnered with keyboard maker Work Louder to launch the Codex Micro, a square-shaped button pad for monitoring and managing AI agents on the Codex coding platform. The limited-run device costs $230 and is separate from OpenAI's hardware project with Jony Ive.

  • Codex Micro is a limited-edition square button pad developed with Work Louder.
  • Priced at $230 and available on Supply Co while supplies last.