Don’t get me improper, I’m up all evening utilizing these instruments.

However I additionally sense we’re heading for an costly hangover. The opposite day, a colleague informed me a few new proposal to route 1,000,000 paperwork a day by means of a system that identifies and removes Social Safety numbers.

I joked that this was going to be a “million-dollar common expression.”

Run the maths on the “naïve” implementation with full GPT-5 and it’s eye-watering: One million messages a day at ~50K characters every works out to round 12.5 billion tokens each day, or $15,000 a day at present pricing. That’s almost $6 million a yr to verify for Social Safety numbers. Even in the event you migrate to GPT-5 Nano, you continue to spend about $230,000 a yr.

That’s a hit. You “saved” $5.77 million a yr…

How about working this code for 1,000,000 paperwork a day? How a lot would this value:

import re; s = re.sub(r”bd{3}[- ]?d{2}[- ]?d{4}b”, “[REDACTED]”, s)

A plain previous EC2 occasion may deal with this… A single EC2 occasion—one thing like an m1.small at 30 bucks a month—may churn by means of the identical workload with a regex and value you a couple of hundred {dollars} a yr.

Which signifies that in follow, firms can be calling folks like me in a yr saying, “We’re burning 1,000,000 {dollars} to do one thing that ought to value a fraction of that—are you able to repair it?”

From $15,000/day to $0.96/day—I do assume we’re about to see a number of firms notice {that a} pondering mannequin linked to an MCP server is far more costly than simply paying somebody to put in writing a bash script. Beginning now, you’ll be capable to make a profession out of un-LLM-ifying functions.