Tesla's Latest Full Self-Driving Beta Update Is Not What Musk Promised

Tesla has updated its controversial Full Self-Driving Beta software to v.11.4.1, and the upgrade is not quite as significant as many Model S, 3, X, and Y owners had hoped

According to Not A Tesla App, the latest FSD rollout, which CEO Elon Musk promised has "major improvements" over the current version, still does not appear to be the system owners want. FSD Beta v11 was released earlier this year, and, comparatively, it's the more substantial upgrade between the two versions. Why?

Because v11 merged Tesla's FSD Beta software stack with the Autopilot software stack, enabling the combined tech of FSD's roads and city streets driving capabilities with the latter's level-two driver-assist system on highways. Despite Musk's words promoting v11.4.1, the technology is still rated at Level 2 self-driving, meaning drivers must pay attention to the road in front of them and be prepared to take manual control of the vehicle at all times.

Level 3, at least for Tesla, still appears to be a long way out. But for now, here are some of FSD v.11.4.1's enhancements:

• Improved control through turns, and smoothness in general, by improving geometry, curvature, position, type and topology of lanes, lines, road edges, and restricted space. Among other improvements, the perception of lanes in city streets improved by 36%, forks improved by 44%, merges improved by 27%, and turns improved by 16%, due to a bigger and cleaner training set and updated lane-guidance module.
• Added lane-guidance inputs to the Occupancy Network to improve detections of long-range roadway features, resulting in a 16% reduction in false negative median detections.
• Improved ego's assertiveness for crossing pedestrians in cases where ego can easily and safely cross before the pedestrian.
• Improved motorbike recall by 8% and increased vehicle detection precision to reduce false positive detections. These models also add more robustness to variance in vision frame rate.
• Reduced interventions caused by other vehicles cutting into ego's lane by 43%. This was accomplished by creating a framework to probabilistically anticipate objects that may cut into ego's lane and proactively offset and/or adjust speed to position ego optimally for these futures.