

EP78: One Week Later: o1-mini o1-preview & Can We Now Build Agents?
Sep 20, 2024
The hosts discuss their experiences with the O1 Mini and O1 Preview, sharing insights on AI coding models and their practical applications. They explore what it takes to create effective AI agents and the balance required between automation and human oversight. The conversation also touches on the impressive capabilities of the Pixtral model and its strengths in image processing. Humorous moments abound, especially while contemplating the philosophical implications of AI free will and sentience. Tune in for a lively mix of tech and lighthearted banter!
AI Snips
Chapters
Transcript
Episode notes
Coding with O1: A Rollercoaster
- Chris used O1 mini and preview for a week, experiencing varying results with coding tasks.
- He found the verbose responses cumbersome but appreciated the improved accuracy and problem-solving abilities.
Verbosity vs. Accuracy
- O1 models offer more complete, trustworthy solutions despite verbose responses.
- The improved accuracy and problem-solving make the verbosity a worthwhile trade-off.
Klarna CRM Experiment
- Chris built a functional CRM with OpenAI's O1, mimicking features like Salesforce.
- It included lead management, visual pipelines, linked data structures, and a functional search feature.