Obama White House’s final tech recommendation: Invest in A.I.

Systems with human-like intelligence still a good 20 years away, says White House CTO

One of the most important things that the U.S. can do to improve economic growth is to invest in artificial intelligence, or A.I., said the White House, in a new report. But there's a dark side to this assessment as well.

A.I.-driven, intelligent systems have the potential to displace millions, such as truck drivers, from their jobs. But potential negative impacts can be offset by investments in education as well as by ensuring there is a safety net to help affected people, the White House argued, in what will likely be the Obama administration's final report on technology policy.

Some of the report's recommendations, which include expanded unemployment help and access to healthcare, may be anathema to a Republican-controlled Congress with a focus on tax reductions and spending cuts. But this report -- "Artificial Intelligence, Automation, and the Economy" (PDF) -- which was in the works well before election day, also describes broader, technological-driven changes that will impact jobs and may pose issues for President-elect Donald Trump.

The "biggest concern" about A.I. "is that we won't have enough of it -- and we won't have enough productivity growth," said Jason Furman, chairman of the White House Council of Economic Advisers, on a telephone press briefing Tuesday. "Anything we can do to have more A.I. will contribute to more productivity growth and will help make possible more wage and income growth."

The report argues that "advances in A.I. technology hold incredible potential to help the United States stay on the cutting edge of innovation," and that the government "has an important role to play in advancing the A.I. field by investing in research and development."

Furman previously put U.S. investment in A.I. research at $200 million a year, but private investments at $2.4 billion a year.

But if you read deeply into the White House report, the future society it describes may be a hostile and desperate one. It will be a society where intelligent machines move up the occupation ladder and the economic benefits go to those with the most skills -- the "fortunate few," and the owners of capital, or the top 0.01% of wealth. In this scenario, inequality grows.

Preventing a dismal outcome will take investment particularly in education, argued Furman. In earlier, manufacturing-related economic shifts, "we were making a really big investment to make sure that people could take advantage of the new types of jobs," he said.

But in recent years, despite the IT revolution, productivity growth has slowed. The productivity growth rate was 2.5% after 1995 but slowed to 1.0% after 2005, the report says.

Furman blames this slowdown in productivity, in part, on a decline in education spending.

"We haven't increased our investment in schooling in the way that we did in the 1930s, 40s and 50s," said Furman. It's "part of why we have seen an increase in inequity in the last couple of decades."

A theme of this report is that "technology is not destiny," meaning that good policy can offset or mitigate the impact of A.I.-driven change.

The White House acknowledges "substantial" uncertainties ahead in forecasting the type and rate of A.I.-driven change, but it warns that those changes can exceed the imaginable.

"There have long been fears that technology -- the machines, the assembly lines, or the robots -- would replace all human labor, but A.I.-driven automation has unique features that may allow it to replace substantial amounts of routine cognitive tasks in which humans previously maintained a stark comparative advantage," the White House report notes.

A.I.-driven machines today have surpassed human performance for some specialized tasks such as image recognition, said Ed Felten, deputy CTO at the White House Office of Science and Technology Policy, who was also on the call.

But, said Felten, in the next 20 years "it's unlikely that machines will exhibit anything that resembles the kind of general-purpose, human-like intelligence that we have."

Join the newsletter!

Error: Please check your email address.

More about Technology

Show Comments