tomtunguz.com · 2024-12-09 · 542d

I Use AI 100 Times Per Hour

Tunguz documents his personal AI usage patterns, finding he invokes AI approximately 100 times per hour across dictation, coding, and analysis tasks. He presents a cost-benefit analysis comparing Claude Opus 4.5 versus Sonnet 4.5, demonstrating that model selection significantly impacts both cost efficiency (86% savings) and performance (36% faster execution). The article argues for a hybrid AI strategy that uses cheaper models for routine tasks while reserving expensive models for complex analysis.

8 metrics· Cited 0× in the knowledge base ·Open source ↗

Metrics in this report

AI Task Cost (Opus 4.5)

0.064USD per task

average

Autonomous task execution in Asana agent monitoring

AI Task Cost (Sonnet 4.5)

0.009USD per task

average

Autonomous task execution in Asana agent monitoring

AI Task Execution Speed (Opus 4.5)

59seconds

average

Autonomous task execution time

AI Task Execution Speed (Sonnet 4.5)

38seconds

average

Autonomous task execution time

Average Transcription Length

18words per call

average

Dictation transcription in email and analysis tasks

Dictation API Call Frequency

51calls per hour

average

Speech-to-text transcription during knowledge work

Token Usage (Opus 4.5)

2456tokens per task

average

Input and output tokens combined

Token Usage (Sonnet 4.5)

1797tokens per task

average

Input and output tokens combined