Robots Can Already Do About 3/4 of US Physical Job Tasks, per Anthropic, but Beat Human Wages on Just 0.3% of Them

Capable is not the same as economical

Anthropic has put numbers on the robot question, and the two headline figures point in opposite directions.

In a study published September 30, researchers Russell Legate-Yang and Maxim Massenkoff scored roughly 19,000 job tasks across about 900 US occupations. They find that robots available today can perform about three-quarters of physical tasks in the US, covering 34 percent of all working hours, though mostly in controlled, purpose-built settings.

But robots are cost-competitive with a human worker for just 0.3 percent of those tasks, the equivalent of roughly 300,000 jobs.

The 40-year problem

Robot prices, adjusted for quality, have fallen about 3 percent a year since the 1990s. At that pace, the study estimates it would take about 40 years for robots to undercut humans on 10 percent of physical tasks.

Even the fast scenario is slow. With costs falling up to four times faster and robots learning new tasks twice as quickly, machines still do not become cheaper than people for half of today's physical work until around 2050.

The exposure map is uneven. Taxi drivers are the most exposed occupation, with robots technically able to do about 97 percent of the work. Warehouse packing is one of the rare cases where the math already works, with a robot costing roughly $2,500 a year less than a human packer. Dishwashing is the opposite: fully doable by machine, at more than three times the human cost. Nurses and mechanics sit near the bottom of the exposure list.

Combined with large language models, about 80 percent of US working time is exposed to one technology or the other.

Do you want to see how to make more plays? Do you want to find gains yourself? Unusual Whales helps you find market opportunities through our market tide, historical options flow, GEX, and much, much more. Create a free account here to start conquering the market with Unusual Whales

Options market and stocks to watch

This study is a cold shower for the fastest versions of the robotics trade, and a roadmap for the patient ones. TSLA carries the market's biggest humanoid-robot premium through Optimus, so any reassessment of automation timelines lands there first.

The economics already work in warehouses, which is where AMZN deploys robots at scale and where SYM sells the automation itself.

NVDA sits underneath all of it as the compute supplier for both training and simulation. Watch call flow in SYM and the warehouse automation names for signs investors are rotating from the humanoid story toward the deployments that pencil out today, and follow AI names on the Unusual Whales news feed.

Want more market intelligence? Create your free Unusual Whales account for options flow, market tide, GEX, and the full toolkit.