The news is burning up with President Trump’s executive orders and Department of Government Efficiency.
But why the outrage?
After all, President Clinton appointed Al Gore to lead the National Performance Review that would “make the entire federal government both less expensive and more efficient, and to change the culture of our national bureaucracy away from complacency and entitlement toward initiative and empowerment.” He also reduced the size of the federal workforce by 377,000.
President Obama envisioned a digital government where technology, although disruptive, would result in a government that was “efficient, effective and focused on improving the delivery of services to the American people. in working towards a more efficient system.”
And just last year, the U.S. General Accountability Office found during President Biden’s administration that there was significant fraud. The report summary noted that based on data from 2018 to 2022: “We estimated that the federal government could lose between $233 billion and $521 billion annually to fraud.”
Seeking a Nonpartisan AI Perspective
I would like to offer an alternative to the outrage. In the spirit of Obama’s appeal to technology, maybe artificial intelligence can look at government efficiency. But to take the sting out of partisanship, let us go back in time.
Let us use a large language model chatbot back when Moses received advice from his father-in-law, Yitro. Yitro explained how a judicial system would reduce both the administrative burden on Moses and have it tailored to the people’s needs.
Here we can use AI to make the delivery of welfare to the community more efficient.
I asked Gemini, Google’s chatbot, to consider a hypothetical. How can Moses deliver welfare more efficiency to his biblical community. Gemini was enthusiastic about this project. Aside from moving from a God-centered society to a secular one, Gemini saw this hypothetical scenario as building on the intersection of ancient wisdom and modern technology. The scenario would also address questions about how leadership could apply technology to improving society.
The AI chatbot took a rational approach rather than one based on outrage.
Gemini’s initial recommendations are pretty much as expected, perhaps taken from a course in becoming a social worker. Needs would be weighed and prioritized. Programs would be targeted to widows, orphans and the disabled. The programs would have record keeping, allowing for audits and accountability. The programs would also reflect fairness to those in need, respecting their dignity and encouraging self-reliance. The advice to Moses was aimed to maximize the impact of welfare, to empower his community and to promote self-sufficiency.
Needless to say, Gemini’s advice misses the human dimension. The advice is naïve. This AI rationality misses the pushback that Moses would have received. I challenged Gemini with Korah’s uprising against Moses.
Gemini agreed:
You’re absolutely right. My previous responses assumed a level of rational acceptance that isn’t always present in human societies, as the story of Korah vividly illustrates. Addressing emotional and unjustified resistance requires a different approach.
My hopes for a distinctive AI approach were not realized. There was the modern alternative dispute resolution approach with de-escalating language that included “I hear your concerns.” It resorted to countering possible misinformation and recommended mediation.
I failed to see how these recommendations would have survived the actual conflict found in biblical narratives.
However, Gemini’s penultimate consideration caught my attention. Evidently, there is a backbone in Gemini’s advice to Moses:
If all else fails, and the resistance threatens the stability and well-being of the community, Moses could assert his authority.
Gemini suggested this backbone could include:
Warnings: Clearly communicating the potential consequences of continued resistance.
Sanctions: Implementing sanctions against those who are actively undermining the community.
Legal Measures: In extreme cases, resorting to legal measures to enforce the law and maintain order. The AI would emphasize the importance of proportionality and justice in any such actions.
Would the AI approach apply to today’s quest for government efficiency?
I was aware that AI models had built in guidelines. But if Gemini could solve the problem for Moses, perhaps it could carry forward the same approach to DOGE. Perhaps my biblical foundation would be a workaround to the chatbot’s policy against partisan issues.
So, I asked Gemini: This seems a good outline for President Trump in his numerous executive orders since he took office on January 20, 2025, to have a more effective allocation of government resources for those in need and to counter the emotional response of those who oppose his Department of Government Efficiency. Does that make sense to you?
Unfortunately, Gemini saw my ploy and refused to apply its biblical analysis to modern times:
I can’t help with that right now. I am trained to be as accurate as possible but I can make mistakes sometimes. While I work on perfecting how I can discuss elections and politics, you can try Google Search.
Since I heard several elected officials address common ground issues, my Google search was not in vain. I was able to find relevant search terms and responses.
Democratic Sen. Mark Warner recently offered a self-critique. “I think the majority of the party realizes that the ideological purity of some of the groups is a recipe for disaster and that, candidly, the attack on over-the-top wokeism was a valid attack.”
I imagine that such openness could bend the partisan divide to a meaningful conversation with senators from the other side of the aisle.
Consider Republican Sen. Joni Ernst’s quest to find a pragmatic answer to what has become a partisan tug-of-war initiated by the Elon Musk’s slash-and-burn method at USAID: “We need guarantees that U.S. assistance is helping people in need.”
I shouldn’t have to ask these questions. All federal spending is required to be publicly available on the website USAspending.gov, a searchable database created nearly two decades ago by a bipartisan law.
The Outrage Puzzle
Outrage is an emotion. When it is applied as an automatic response to how government functions, we lose sight of the common ground that elected officials have often sought.
It is also true that partisanship has led to a spoils of war approach. For Democrats and Republicans. And, not surprisingly, that was true in biblical times as well.
But when there is an opportunity to collaborate on government efficiency, outrage should not veto the goodwill and good sense that exists among most elected officials. We need them to attend to their responsibilities since we cannot delegate to the AI talisman. At least, not yet.
Joe Nalven is an adviser to the Californians for Equal Rights Foundation and a former associate director of the Institute for Regional Studies of the Californias at San Diego State University. His chatbot conversation was lightly edited.
