Tesla amplified a Full Self-Driving clip on September 10, 2026, and credited photon count reconstruction for how the system handled a car that was nearly invisible to a human driver in direct sunlight.
The official Tesla account quoted owner Ananto Mohammad’s dashcam-style video with a short line — “Photon count reconstruction FTW” — pointing to the same raw-sensor approach Tesla has used to explain why FSD can keep working when glare washes out a normal camera view. In the clip, Mohammad said sunlight was hitting the camera so hard he could not see the other car until the last moment, while FSD spotted it early and handled the scenario cleanly.
Owners on Hardware 4 currently run FSD Supervised around v14.3.7, while Hardware 3 cars are on v14.1 Lite via 2026.21.6. Tesla did not name a software build in this amplify, so that context is the broader owner fleet picture rather than a claim about the clip itself. The company has previously described feeding higher-bit-depth photon-count streams into its vision networks instead of heavily processed RGB images, which helps preserve detail at the bright and dark extremes.
The post lands alongside other recent Supervised FSD showcases, including v14.3.9 automatic collision evasion and owner stories Tesla has been amplifying. For drivers who have watched sun glare erase an entire lane of traffic, the official tip of the hat to photon count reconstruction is a useful reminder of why Tesla keeps arguing that cameras plus AI can see past conditions that beat the human eye.
Want to see more of our stories on Google?
P.S. — Buying a new Tesla? Click here to save $1,000 USD, while supporting independent news.
Help support us by shopping on Amazon here.
Links in this post are affiliate links, so we earn a tiny commission at no charge to you. Thanks for supporting independent media!
