Real Alpha
Try Pro free

Future of Life Institute Podcast · 3 min · Sep 25, 2026

Computer vision struggled when Ukraine's battlefield changed

Katrina Manson · Reporter, Bloomberg

Katrina Manson describes algorithms that failed to recognize Russian tanks because they had been trained on different terrain.

The episode’s best minutes

Full analysis
  1. 8:42AI sharply increased the number of targets the military could strike7 min
  2. 17:43Computer vision struggled when Ukraine's battlefield changed3 min
  3. 23:30Targeting doctrine is shifting from human decisions to oversight3 min
  4. 4 more moments in the full episode
“It had been trained on the desert. It had been trained on the jungle in the Philippines.”
Katrina Mansonat 18:14 · Future of Life Institute Podcast
18:14

Takeaways

  1. Algorithms trained on desert and jungle imagery missed Russian tanks.
  2. Some reported accuracy fell as low as 10%.
  3. Retraining helped, but humans still had to explain battlefield context.

About this segment

Katrina Manson describes algorithms that failed to recognize Russian tanks because they had been trained on different terrain. The example shows how quickly model reliability can falter in a new war.

Katrina Manson

Katrina Manson is author of Project Maven: A Marine Colonel, His Team, and the Dawn of AI Warfare.

Investigated the US military's AI use and chronicled the Pentagon's Project Maven program in her book.

  • GD

    Gus Docker, Host · Host, Future of Life Institute Podcast

From “Can Humans Still Control AI-Assisted Kill Chains? (with Katrina Manson)”, Sep 25, 2026. Watch the full episode

Answers “Is AI dangerous?” See all 112 answers

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 17:47

    of how the system might fail? Yes. So some of my reporting for the book focused on the work that the US did for Ukraine. And there, there was a team based in Germany that was using computer vision to try and find objects for the Ukrainians to hit Russian enemy objects. And in the first few days of the war of Russia's invasion of Ukraine, computer vision couldn't recognize the Russian tanks. It had been trained on the desert. It had been trained on the jungle in the Philippines. It wasn't used to Ukrainian, European, and increasingly snowy conditions.

  2. 18:28

    And so what they did was they took the algorithms, they took new pictures of the tanks, and they retrained the algorithms on these tanks. And so then the validity, the accuracy of the algorithms started to increase, but in the opening days of the invasion of Ukraine, US algorithms successes really plummeted. I'm told sometimes down to 30% accuracy, in some cases down to 10% accuracy. And that was one of the major findings for me in the book that in the opening days of a war, which is when AI would be hoped to help speed up a war, actually, it's having to adapt to so many new realities, it wasn't a reliable tool.

  3. 19:13

    Now, when they improved the algorithm accuracy by training it against pictures of Russian tanks, those scores started to go back up. And I still found that there were key examples where a mathematician or someone producing an algorithm wasn't sufficiently aware of how a war actually takes place. And the example I came across was that the Russians arranged their TELs, their transporter erector launchers, which are essentially mobile missile launchers, in a semicircle.

  4. 19:44

    Now, from above, from a satellite perspective, they really just look like trucks. And so for an algorithm searching for a military object, it would be very difficult to isolate a mobile missile launcher from a truck. And obviously, the intention is not to hit civilian trucks. and so the algorithm vendors didn't know about this semicircular arrangement the u.s operators did but they didn't know if they were allowed to tell the algorithm vendors so you have a kind of communication problem between humans about how to use these machines that was from the u.s perspective inhibiting their ability to actually be able to use algorithms to recognize these objects of war i found that a really instructive example overall they sped up though and And I learned in the book that on one occasion, the Ukrainians were able to target 267 items

  5. 20:40

    in one day because of the information passed to them from the US using MavenSmart system.