The system aims to serve as an ‘ethical’ and ‘legal’ veneer for future military automation efforts.
Palantir already sells its domestic surveillance services to US Immigration and Customs Enforcement, so it should come as no surprise that the company founded by billionaire Peter Thiel is working to make inroads into the Pentagon as well. On Tuesday, the company released a video demo of its latest offering, the Palantir Artificial Intelligence Platform (AIP). While the system itself is simply designed to integrate large language models (LLMs) like OpenAI’s GPT-4 or Google’s BERT into privately-operated networks, the very first thing they did was apply it to the modern battlefield.
In the video demo above, a military operator tasked with monitoring the Eastern European theater discovers enemy forces massing near the border and responds by asking a ChatGPT-style digital assistant for help with deploying reconnaissance drones, ginning up tactical responses to the perceived aggression and even organize the jamming of the enemy’s communications. The AIP is shown helping estimate the enemy’s composition and capabilities by launching a Reaper drone on a reconnaissance mission in response the to operator’s request for better pictures, and suggesting appropriate responses given the discovery of an armored element.
“LLMs and algorithms must be controlled in this highly regulated and sensitive context to ensure that they are used in a legal and ethical way,” the video begins. To do so, AIP’s operation is based on three “key pillars,” the first being that AIP will deploy across a classified system, able to parse in real-time both classified and non-classified data, ethically and legally. The company did not elaborate on how that would work. The second pillar is that users will be able to toggle the scope and actions of every LLM and asset on the network. The AIP itself will generate a secure digital record of the entire operation, “crucial for mitigating significant legal, regulatory, and ethical risks in sensitive and classified settings,” according to the demo. The third pillar are AIP’s “industry-leading guardrails” to prevent the system from taking unauthorized actions.
A “human in the loop” to prevent such actions does exist in Palantir’s scenario, though from the video, the “operator” appears to do little more than nod along with whatever AIP suggests. The demo also did not elaborate on what steps are being taken to prevent the LLMs that the system relies on from “hallucinating” pertinent facts and details.