AI News Today | Julian Goldie Podcast

Grok 4.5 VS Claude Opus 4.8: Who Wins?

11 min · 9. juli 2026
episode Grok 4.5 VS Claude Opus 4.8: Who Wins? cover

Description

Grok 4.5 vs Claude Opus 4.8: Side-by-Side Game Builds, Real-World Tests (Goldiebench)The video compares Grok 4.5 and Claude Opus 4.8 side by side using Goldiebench, emphasizing real-world performance over benchmarks across multiple game and creative tasks. Grok 4.5 generally produces more playable, smooth 3D games and wins many rounds where Opus 4.8 fails to generate or is too buggy, though Opus performs better in some cases like a driving game, an edited Remotion video, and a flight simulator, and also wins a few specific games. The creator notes Grok can be slow and less agentic in chat and wouldn’t use it for agent workflows unless generating images/videos, while preferring Opus 4.8 for building systems, workflows, and an Agent OS. The video ends by promoting the AI Profit Boardroom for access to Agent OS, agents, tutorials, and community support.00:00 Grok vs Opus Setup00:38 Why Real Tests Matter00:57 Crypt Game Showdown01:34 Dragon Realm Faceoff02:15 Racing and Skyrim Tests03:41 Twilight and VoxelCraft04:43 Runner and Driving Results05:26 Video Edit and Flight Sims06:36 Agentic Use in Hermes07:04 More Games and Scoreboard09:24 Final Verdict and Picks10:39 Boardroom Offer and Outro

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

594 episodes

episode Agent OS: GPT 5.6 + VPS + FREE Apis! artwork

Agent OS: GPT 5.6 + VPS + FREE Apis!

AI Profit Boardroom Q&A: Agent OS Sync Across Macs, ChatGPT Work, AI Avatars, Omniroute & Omi on WindowsThe host answers recent AI Profit Boardroom questions, including how to sync an Agent Operating System across five Macs by using Google Workspace/Drive with a shared API access token or running all Agent OS instances on a VPS and saving files locally (with tutorials using Cloudflare and Hostinger). He explains the latest ChatGPT app where Codex is rebranded to ChatGPT Work, combining chat and project-building features and supporting tasks like building apps, websites, videos, integrations, and scheduled tasks. He covers tools and training for creating AI avatar videos for training courses, citing high Twitter impressions and community examples. He advises how to use the free Omniroute/Omniroot coding API with various agents and troubleshoot “fetch failed,” and shares an Omi alternative for Windows that can sync with Obsidian via plugins.

Yesterday9 min
episode NEW ChatGPT 5.6 & Codex Update artwork

NEW ChatGPT 5.6 & Codex Update

The script tests Codex rebranded as ChatGPT using GPT 5.6, showing how to switch between speed/effort settings and run multiple tasks. The creator builds and pins projects, demos a working habit tracker, and uses “computer use” to have ChatGPT navigate a Skool group and publish a personalized public post. They link Descript via a plugin to edit a video by removing filler words and adding effects, and start installing Hermes Agent from GitHub in a separate project folder while a new AI Profit Boardroom website is generated. The finished site is compared to an older version and praised for a modern design, CTAs, animations, and functional FAQ. The video ends by highlighting use cases (websites, social content, video editing, automation, image generation) and promoting the AI Profit Boardroom community and trainings.

Yesterday15 min
episode GPT-5.6 FULL COURSE 1 HOUR (Build & Automate Anything) artwork

GPT-5.6 FULL COURSE 1 HOUR (Build & Automate Anything)

This one-hour course shows how to access and use GPT 5.6 in ChatGPT, switch models and effort levels, and automate workflows like generating X posts in a consistent style by training on past content and using web browsing. It covers image creation with ChatGPT Image 2.0, running parallel workflows, and using Deep Research with editable plans. The script explains organizing work with Projects, sources, and custom instructions, plus building and sharing Custom GPTs via the GPT Store. It also demonstrates scheduled tasks, improved voice mode, plugins like Google Drive for creating documents, and saving prompts with Text Expander. The second half introduces Codex for agentic building: creating websites via Sites, working locally or in the cloud with permissions, using computer-use to operate a browser, scheduling tasks, and adding skills like Remotion/Hyperframes to generate videos, with deployment examples via Netlify and a pitch for the AI Profit Boardroom.

Yesterday1 h 2 min