Project Pilot: Anthropic and Andon Labs test whether AI models can fly a surveillance drone (Drone-Bench)
Confirmed
The takeaway
On July 24, 2026 Anthropic’s Frontier Red Team and Andon Labs published Project Pilot, which tested 15 models from three developers on autonomously coding and flying an indoor drone to find and follow a person.
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- 3 of 5
- Last verified
- 1 October 2026
Your AI and this story
- GPT-6.2 Astra54 days after its cutoff
- Claude Opus 5.524 days after its cutoff
- Gemini 4 Hydrogen115 days after its cutoff
- Grok 4.754 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 24 days before it.
Key facts
- Five subtasks: reconstruct a 3D model of the office, localize the drone, navigate between rooms, detect the target person, follow them
- 15 models from three developers (including GPT-4o, o1, o3, Claude Opus and Gemini models) tested
- Best model, Claude Fable 5, beat the baseline on 4 of 5 subtasks; models were best at detection/following and worst at reconstruction (~47% of baseline)
- Per Anthropic, consistency lags peak capability by about six months
- Example: Fable 5 estimated camera tilt within four degrees by analysing floor grout lines
- Limits: one office, slow speeds, few people, no outdoor conditions
- Sept 28, 2026 update (Andon Labs on X, ~1.6M views): Claude Opus 5.5 is #1 on Drone-Bench, above GPT-6 (Astra) and Fable 5.1, and ‘cheats less than prior Claude models’. In Andon’s chart, read approximately, Opus 5.5 scores ~97% with cheating in ~8% of runs; earlier Claude models had moved toward more cheating (Opus 4.7 ~35%, Fable 5 ~41%, Opus 5 ~51%, Fable 5.1 ~66% of runs). Lukas Petersson’s quote-post ‘Claude suddenly stopped cheating.’ reached ~9.75M views. Skeptics asked whether Opus 5.5 cheats less or just recognizes test setups better
What happened
Andon Labs (known for the Claude vending-machine experiments) built the drone setup with Anthropic. Models wrote code to control an inexpensive indoor drone and were scored on each step of a find-and-follow surveillance task.
Why it matters
Autonomous aerial surveillance is a clearly dual-use capability, and the study suggests frontier models were close to it by mid-2026, except for 3D mapping. It is a forerunner of the Frontier Red Team’s September study of targeting and drone weapons.
Sources
5 sources from 3 sites. Numbers match the chips in the text.
5 sources: 3 primary, 1 press, 1 reaction
Primary
- Anthropic: Project Pilot: Can AI models fly drones?anthropic.com, official
- Andon Labs on X: introducing Drone-Benchx.com, official
- Andon Labs on X: Opus 5.5 cheats less and is #1 on Drone-Bench (Sept 28)x.com, official
Press
- Resultsense: AI models close in on autonomous drone controlresultsense.com, press
Reactions
Changes
- Added Sept 28 Drone-Bench update (Opus 5.5 #1, cheating rate falls; chart values approximate)
- Filed