I Tested Codex's NEW $500/mo Ultrafast mode
A reviewer tests Codex's new $500/month Ultrafast mode, which claims to be 8x faster than standard mode. While results vary by task complexity, Ultrafast delivers significant speed improvements but at substantially higher resource consumption, making it suitable primarily for time-sensitive projects.
Summary
The speaker demonstrates Codex's newly announced Ultrafast mode, available exclusively on a $500 per month plan. The mode is marketed as 8 times faster than standard mode and 4 times faster than regular fast mode. In the first test, the speaker asks the AI to summarize a 54-minute community Q&A call, which Ultrafast completes in 19 seconds. However, the most resource-intensive task tested involves creating a 60-second video from 145 GB of footage about a Google trip to San Jose. Here, Ultrafast takes approximately 19 minutes and consumes 17% of the weekly limit, while standard mode takes 50 minutes and uses only 4% of the limit—resulting in approximately 4.25 times higher resource consumption. The speaker notes that the standard mode output in this case seemed inferior and possibly generated by a different, lower-quality model. In a third test creating a YouTube resource guide from video content, Ultrafast performs closer to the 8x marketing claim, completing the task in 1 minute 43 seconds compared to standard's 13 minutes. The speaker concludes that Ultrafast is most valuable when time-sensitive deadlines are critical, such as meeting preparation, but emphasizes the significant cost trade-off.
Key Insights
- Ultrafast mode delivered 19-second summaries of 54-minute video calls, demonstrating exceptional speed for AI summarization tasks.
- The 145 GB video project revealed that Ultrafast consumed 17% of weekly limit versus standard's 4%, meaning 4.25 times higher resource consumption despite the claimed 8x speed advantage.
- The speaker observed that standard mode output on the video project appeared to be generated by a different, lower-quality model than the Ultrafast version, suggesting quality differences beyond just speed.
- On the YouTube resource guide task, Ultrafast achieved 1 minute 43 seconds versus standard's 13 minutes, representing approximately 7.5x speed improvement and closely matching the 8x marketing claim.
- The speaker recommends using Ultrafast primarily for time-critical scenarios such as last-minute meeting preparation, acknowledging the substantial premium cost as a limiting factor for regular use.
Topics
Transcript
[0:00] The new ultrafast from Codex is really fast. I just asked, " What did I talk about on this week's Q&A call with the community?" And you see how quickly he will find the right call, get the transcript, and summarize it. It was a 54-minute call that needed to be reviewed and summarized, and he did it in 20 seconds. Or, sorry, in 19 seconds. The thing is, ultrafast is only available on their new plan, which they just announced for $ 500 per month. This is the fastest way to create projects with Astra and Codex. It is eight times faster than standard and four times faster than regular fast mode. I asked Astra to create a…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Nate Herk | AI Automation
Every Codex Concept Explained for Non-Coders
A comprehensive tutorial explaining 18 core Codex concepts for non-technical users, organized into four parts covering basics (projects, agents, agent loops, goals), environments (on-premises vs. cloud, working trees), customization (AI models, effort levels, permissions, skills), and scaling tools (browser, sites, subagents, scheduled tasks, voice mode).
Claude Code Mods Are Game Changers. This One Saves Me Money.
Claude Code now supports mods that allow customization of the Cloud desktop app. A user demonstrates a cache management mod that tracks usage data, displays costs, monitors session limits, and provides notifications before cache expiration to help optimize spending.
5 Claude Code Mods That Everyone Needs
The video demonstrates five useful Claude Code modifications (mods) that are plugins enabling customization of the Claude desktop application interface. The creator showcases practical mods including Cache Keeper for token management, Recording Mode for privacy, Goal tracking interface, and Collision Guard for file conflict detection, explaining how anyone can create mods using plain language.
How to Actually Build & Sell Software with AI as a Non-Techie
Dave Fabrikant, a 10+ year Python programmer and AI engineer, discusses how AI coding tools have transformed software development from a specialized skill into an accessible field for non-technical founders. He explains the progression from personal tools to scalable products, emphasizing architecture, security best practices, and the shift from specification-driven to intent-based development.
I Tested Opus 5.5 vs Sonnet 5.5
A comparison test between Claude Opus and Sonnet 3.5 shows that while Opus costs twice as much, it doesn't deliver twice the value across all tasks. Sonnet excels at well-defined requests with faster speed and lower cost, while Opus outperforms on vague, creative tasks requiring deeper reasoning.