Claude alone took 3 minutes. With Jev, 21 seconds.
A demonstration comparing AI slide deck creation using Claude alone versus Claude integrated with Jev, showing that the hybrid approach completed the task in 21 seconds for $8 with proper formatting, while Claude-only took 3+ minutes and cost $49 with poor formatting.
Summary
The speaker presents a comparison of two approaches to AI-powered slide deck creation, illustrating the emerging era of AI automation efficiency. In the first approach, using only Claude (OPUS 5 LLM), the process took 3 minutes and 13 seconds, cost $49, and produced a slide deck with improper formatting and incorrect fonts. In contrast, using Claude integrated with Jev—a tool that works in conjunction with AI models—completed the identical task in just 21 seconds for only $8, with beautiful design and proper formatting. The speaker emphasizes this cost and time differential as "mind-blowing." The key difference in workflow is that Jev handled the layout selection in 900 milliseconds, while Claude provided the content creation. The speaker demonstrates the step-by-step processes each system followed, revealing that when tools are properly distributed between specialized AI agents, efficiency dramatically improves. The main insight is that the bottleneck was content creation time, not layout design, and that this hybrid approach shows how AI agents can be optimized for maximum efficiency.
Key Insights
- Claude alone took 3 minutes 13 seconds and cost $49 to create a slide deck with improper formatting and incorrect fonts
- Claude integrated with Jev completed the same slide deck task in 21 seconds for $8 with proper design and formatting
- In the hybrid approach, Jev handled layout selection and completed that portion in just 900 milliseconds
- The actual time bottleneck in the optimized workflow was content creation rather than layout or design selection
- Distributing specialized tasks between different AI agents significantly improves overall efficiency and cost-effectiveness
Topics
Transcript
[0:00] We are entering a new era of AI automation. I show you here a very quick example that shows how powerful and cost effective this new model really is. I let AI create a slide deck for me where I used only the LLM Claude in this case OPUS 5 and another one where Jeff is in the loop. To be clear, Jeff is integrated with my AI models. So Claude is using Jeff to speed things up. And here is the mind-blowing part now. 21 seconds later, I have this full slide [0:31] deck created, beautifully looking, perfectly designed, and it cost me 8. Compare this to the LLM only version, which took 3 minutes and 13 seconds…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
Why I stick to Claude for work (most of the time)
The creator demonstrates why Claude is their preferred AI for work by comparing it with ChatGPT across multiple tests, showing that Claude better adheres to custom instructions and agentic workflows defined in local folder structures. The key advantage lies in using organized, LLM-agnostic folder systems with agents.md files rather than relying on auto-memory features.
You are using the wrong Claude for work! (Here is proof)
A video demonstrating that Claude Code is significantly more powerful than Claude Cowork for professional knowledge workers, showing how Claude Code better understands folder context, enforces safety rules, orchestrates sub-agents with different models, and creates persistent file outputs rather than temporary artifacts.
Obsidian is the tool I teach in. Keep the one you have.
The creator addresses criticism about switching to Obsidian after previously promoting other tools, clarifying that his tool-agnostic ICOR methodology remains unchanged and that Obsidian is simply an interface layer for his folder-based system. He emphasizes that the underlying folder structure, AI automation, and productivity principles are identical regardless of which tool visualizes the content.
Claude sucks. And here is why.
This video explores why Claude and other AI models produce inconsistent results, examining how model selection (Haiku vs Sonnet vs Opus vs Claude 3.5 Fable), effort levels, prompt clarity, and system context dramatically affect output quality. The speaker demonstrates these differences through a Venn diagram creation task and advocates for using organized folder systems with documented SOPs and code-based solutions to ensure consistent AI performance.
Claude can now prompt its own SESSIONS. I built the boss.
Claude now has the ability to interact with multiple sessions, allowing a streamlined orchestration of tasks through an agent called Larry. This integration can simplify task management and enhance productivity by enabling a single main session to oversee various sub-sessions or tasks.