AI News Today | Julian Goldie Podcast

China's MiniMax M3 AI Changed Everything

9 min · 4. juni 2026
episode China's MiniMax M3 AI Changed Everything cover

Description

China’s MiniMax M3: The AI “Night Shift” That Works 24/7 for a Fraction of the CostThe script introduces MiniMax’s new Chinese AI model M3 (released June 1) and claims it beats major U.S. models like GPT 5.5 and Gemini 3.1 Pro on certain coding benchmarks at a much lower price. It highlights an internal MiniMax test where M3 worked autonomously for 24 hours, making nearly 2,000 moves across 147 attempts without human intervention, noting the results are from MiniMax’s lab and not yet independently verified. The core idea is shifting from using AI as a single chatbot to running it as a coordinated “team” that can operate a “night shift,” continuing work while you’re offline. It describes integrating M3 into an agent operating system with shared memory and pairing it with Hermes as the “hands” to execute tasks, enabling image, video, and voiceover creation from one dashboard.00:00 [https://www.youtube.com/watch?v=kTSvAAeehy8] MiniMax M3 Bombshell00:21 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=21s] Benchmarks and 24 Hour Test01:02 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=62s] Chatbot to AI Team01:48 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=108s] The Night Shift Framework02:15 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=135s] Agent OS Demo Setup02:50 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=170s] Million Word Memory03:20 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=200s] Multimodal Studio Powers03:50 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=230s] Hermes Hands Integration04:15 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=255s] Live Workspace Walkthrough05:32 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=332s] Not Techy Setup Objection05:51 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=351s] AI Profit Boardroom Offer06:39 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=399s] Why This Model Matters06:58 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=418s] Stubbornness Beats Quitting07:30 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=450s] Putting the System Together08:07 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=487s] Don't Wait Start Now08:43 [https://www.youtube.com/watch?v=kTSvAAeehy8&t=523s] Final Call to Build Yours

Comments

0

Be the first to comment

Sign up now and become a member of the AI News Today | Julian Goldie Podcast community!

Get Started

1 month for 9 kr.

Then 99 kr. / month · Cancel anytime.

  • Podcasts kun på Podimo
  • 20 lydbogstimer pr. måned
  • Gratis podcasts

All episodes

573 episodes

episode China’s Tencent Hy3 is FREE & Opensource! artwork

China’s Tencent Hy3 is FREE & Opensource!

Tencent Hunyuan HY3 (295B) Is FREE for 2 Weeks: How to Run It via OpenRouter + Hermes (Honest Tests)The video covers Tencent Hunyuan HY3, a new free, open-source 295B-parameter mixture-of-experts model from China, available on Hugging Face and reportedly outperforming DeepSeek and Qwen on some benchmarks. The host explains two free ways to run it (including a free OpenRouter API trial until July 21) and shows using it inside an agent operating system to generate code like a landing page in real time, as well as integrating it into Hermes tools via a portal offering a two-week free window. They share honest comparisons from their own tests versus GLM 5.2 and models like Opus 4.8 and “Fable 5,” concluding HY3 can be useful for agentic and auxiliary sub-agent tasks but doesn’t replace top models, though it impressed by generating a fully animated video via Remotion. The episode ends with a pitch for the AI Profit Ballroom community, guides, and the agent OS.00:00 [https://www.youtube.com/watch?v=VQRx067VlWQ] HY3 Model Overview00:19 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=19s] Benchmarks and Hype00:42 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=42s] Run It Free via OpenRouter01:42 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=102s] Hermes Integration Options02:16 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=136s] Honest Model Comparisons02:49 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=169s] Real Project Demos05:00 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=300s] Best Use Cases and Workflows06:05 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=365s] Agentic Focus and Bench Claims06:31 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=391s] Video Creation Test07:28 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=448s] Wrap Up and Next Drops07:58 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=478s] Community and Guides Pitch08:54 [https://www.youtube.com/watch?v=VQRx067VlWQ&t=534s] Final Thanks

Yesterday8 min
episode Claude Agent OS is INSANE! 🤯 artwork

Claude Agent OS is INSANE! 🤯

Inside My Claude Agent Operating System (Agent OS): Voice Agents, Content Factory, Memory & Token DietThe script explains the creator’s Claude Agent Operating System, a unified setup where multiple agents (e.g., Hermes, OpenClaude, Claude, Antigravity, Codex) share a common memory that auto-logs updates so agents learn the user’s voice, brand, goals, projects, and clients. It showcases recent additions like Hermes Apollo (a voice-activated agent), Hermes Oracle (pulls trending news and can publish content to a website), and Hermes Astros (keyword/topic monitoring that generates daily content ideas and routes prompts to agents). The system includes a command deck for mission control, model layers with premium and free options, an agent fleet and Kanban workflow from plan to ship, and token-minimization tools (RTK, Caveman, Ponytail). It also features a content factory, studios for design/games/AI movies, and an Obsidian-based “memory galaxy,” and is offered via the AI Profit Boardroom with tutorials, community support, and coaching.00:00 [https://www.youtube.com/watch?v=IoGZVpsSCK0] Agent OS Overview01:01 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=61s] Voice Agent Hermes Apollo01:42 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=102s] News Oracle Automation02:38 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=158s] Keyword Ideas Engine03:23 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=203s] Kanban Agent Teams03:50 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=230s] New Integrations Added04:23 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=263s] Access and Installation04:46 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=286s] System Layers Explained04:54 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=294s] Command Deck Mission Control05:21 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=321s] Models and Agent Fleet06:19 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=379s] Ideas Pipeline Workflow06:44 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=404s] Token Diet Strategies07:37 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=457s] Content Factory Automation08:26 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=506s] NotebookLM Content Library09:15 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=555s] Studios Design Games Movies09:56 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=596s] Memory Galaxy in Obsidian10:48 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=648s] Community Wins and Proof12:02 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=722s] Why Systems Beat Models13:08 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=788s] Boardroom Support and Coaching13:51 [https://www.youtube.com/watch?v=IoGZVpsSCK0&t=831s] Classroom Training and Wrap Up

Yesterday14 min
episode Hy3 Destroys GLM 5.2? artwork

Hy3 Destroys GLM 5.2?

GLM 5.2 vs Tencent Hunyuan HY3 (HY3): Side-by-Side Tests + Final VerdictThe script compares GLM 5.2 (from ZAI) versus Tencent Hunyuan HY3 (HY3) side by side using multiple generated projects, including game-like demos (Dragon Realm, flight sim, driving game, parachute game) and a Remotion cinematic video. HY3 is described as buggy, laggy, and often lacking detail, requiring hours of back-and-forth to get usable outputs, while GLM 5.2 generally produces smoother, more playable results on the first try. HY3 wins one round where GLM 5.2 fails, but GLM 5.2 wins 6 of 7 tests overall and also has a larger context window (1M tokens vs 256K). HY3’s advantages are free API access (via OpenRouter until July 21) and availability via Hermes Agent, while GLM 5.2 is preferred overall.00:00 [https://www.youtube.com/watch?v=sknWbKXUqTU] GLM vs HY3 Intro00:26 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=26s] Free Access Setup00:52 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=52s] Test 1 UI Smoothness01:49 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=109s] Dragon Realm RPG Test02:50 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=170s] Flight Simulator Showdown03:25 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=205s] Neon City Driving Test04:12 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=252s] When GLM Fails04:41 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=281s] Parachute Game Comparison05:05 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=305s] Remotion Video Ad Test05:45 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=345s] Scorecard and Context06:13 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=373s] HY3 Strengths and Tips07:00 [https://www.youtube.com/watch?v=sknWbKXUqTU&t=420s] Final Verdict and Outro

Yesterday8 min
episode How to Run Hermes Agent FREE Forever! artwork

How to Run Hermes Agent FREE Forever!

Run Hermes Agent FREE Forever with OmniRoute (231+ Providers, Auto-Fallback & Token Compression)The script demonstrates how to run Hermes Agent for free using the newly released open-source OmniRoute/Omniroot gateway, which routes requests across 231–237 providers with millisecond auto-fallback when a free API is rate-limited. It explains that OmniRoute compresses tokens using RTK (removes repetition/duplication) and Caveman (short, blunt outputs) to reduce rate limits, and offers one endpoint that Hermes can use without “knowing the difference.” The creator shows testing Hermes with an OmniRoute profile, building a landing page locally, and recommends using separate Hermes agent profiles per API/model to compare side by side. Setup is described as non-technical via simple terminal commands and GitHub instructions, with examples of free-forever providers and optional OpenRouter integration. The video also promotes the AI Profit Boardroom and its Hermes Agent OS workflows, memory system, community support, and coaching calls.00:00 [https://www.youtube.com/watch?v=gGL5dKf-rVA] Free Hermes Setup01:01 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=61s] OmniRoute Benefits01:43 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=103s] Hermes Profiles Demo02:57 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=177s] How Routing Works03:55 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=235s] Workflows and Memory04:33 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=273s] Dashboard Setup Steps05:51 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=351s] Free Providers List06:29 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=389s] Token Compression Explained07:01 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=421s] Wrap Up and Results07:23 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=443s] Agent OS Offer08:24 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=504s] Community and Coaching08:50 [https://www.youtube.com/watch?v=gGL5dKf-rVA&t=530s] Final Thanks

Yesterday8 min