These dogs sure are barkin’.
A machine learning expert successfully integrated ChatGPT into the famous robodogs made by Boston Dynamics — a high-tech product that both the NYPD and FDNY have recently rolled out.
Techie Santiago Valdarrama merged the program into the yellow-and-black four-legged bots. It was done as a way to enhance “automated missions” the robots were running to assess factors of their nearby environment.
Now users can speak directly to the robodogs and it will answer “in plain English,” he posted on Twitter along with a clip of the GPT hounds in action.
“Each mission uses miles-long, hard-to-understand configuration files. Only technical people can handle them. At the end of each mission, the robots capture a ton of data. There’s no simple way to query all of it on demand,” Valdarrama wrote.
“That’s where ChatGPT comes in. We show it the configuration files and the mission results. We then ask questions using that context. Put that together with a voice-enabled interface, and we have an awesome way to query our data!”
Now, the robots can respond to questions “in real time” for both its past and future objectives, according to Valdarrama, who had pre-programmed in commands related to specific contexts.
Fellow tech expert Raul Junco described the integration as a “game changer.”
As far as what this pairing is capable of moving forward, “your imagination is pretty much the limit,” the AI expert boasts. Its current uses are for detecting thermal anomalies, reading both analog and digital gauges, detecting acoustic anomalies in addition to rust, as well as identifying changes to its environment.
In practical use during April, the FDNY utilized their non-ChatGPT robodog to do search and rescue inside of the collapsed parking garage in lower Manhattan.
Though, one user commented concerns that the major technological breakthrough could yield a “wild west” scenario with the power it wields. Others also expressed fear over what this could mean moving forward.
“We are limiting ChatGPT to answer questions from a context we generate, so there’s no way to get any other text. ChatGPT can’t control the robot at all. It’s just conversational,” Valdarrama wrote.
“We do think about ethics and safety. I promise you, pesticides on your food are about 100x more dangerous than this.”