Robots now run AI-written code without an AI calling the shots, succeeding 92% of the time
Image by AI Robots now run AI-written code without an AI calling the shots, succeeding 92% of the timeRobots completed 221 of 240 trials using Claude-written programs for tasks such as uncapping bottles. Human help was...
Bitcoin 1 Minute
A notable development has hit the crypto markets. Image by AI Robots now run AI-written code without an AI calling the shots, succeeding 92% of the timeRobots completed 221 of 240 trials using Claude-written programs for tasks such as uncapping bottles. Human help was available during development, not execution. By Liam 'Akiba' Wright Editor-in-Chief Nov.
15, 2026 at 2:40 pm GMT 2 min read Quick Take 01 ACE-CaP-0 researchers report 221 successes in 240 physical trials across eight frozen task programs. 02 Programs used live perception and control during evaluation, with no human or coding agent in the execution loop. 03 Development allowed human guidance and demonstrations; consistency across separate development runs and reuse under new conditions remain open.
Market Dynamics
Make preferred on Share Share Robot programs developed by Anthropic’s Claude Opus 5. 5 coding agent completed 221 of 240 physical evaluation trials, ACE-CaP-0 researchers reported in a study posted November 12. The result shows that task-specific skills can persist in code and run without the coding agent choosing each action.
The researchers behind ACE-CaP-0, a method for developing robot control programs, reported a 92. 1% success rate across eight tasks. Each program was frozen before 30 separate evaluation trials, with no further updates.
Human guidance and demonstrations were available during development. The experiment separates program development from repeated execution. The agent's work produced a program that could be used repeatedly.
Market Impact
During evaluation, that program still used perception and control systems to respond to observations, while its decision rules stayed fixed. Neither a human nor the coding agent remained in the execution loop. The coding agent leaves.
ACE-CaP-0 separates assisted program development from repeated execution with live perception and control. Human assistance is available during development; the frozen task program runs without a human or coding agent in the execution loop. Authors' preprint account.
Development permits human assistance; demonstration-collection resets are excluded from the ten-reset budget. Repeated execution on tested tasks does not establish reuse under new conditions. Sources and evidence SourcesACE-CaP-0 methods and evaluationNovember 12 preprint abstractSupporting factsIn ACE-CaP-0's evaluation, each task program remained unchanged while runtime perception and control stayed active; neither a human nor a coding agent was in the execution loop.
This shift continues to shape the digital-asset landscape, with analysts examining its near-term effects.





