🩻 Radiologist & MRI clinic owner | Chaired committee writing U.S. MRI accreditation standards | Filmmaker | All tweets IMO | No investment/medical advice
Joined May 2013
- Tweets 28,832
- Following 2,241
- Followers 3,591
- Likes 22,320
723 Photos and videos
Pinned Tweet
Where is the best place in the U.S. to have a whole-body MRI wellness screening? Grok’s answer: MRIatbelfair.com
3
3
13
1,563
Optimus V4 goal. @Tesla_AI x.com/BredsguardDalen/status…
1
26
A. Joseph Borelli, Jr., MD retweeted
Jun 11
The best one ever.
I shall be summoned
103
103
3,151
87,309
A. Joseph Borelli, Jr., MD retweeted
Jun 10
Another user @realCarnasis submitted this crash footage of his Tesla being T-boned while FSD was engaged. Raw video analyzed using @CamCutApp telemetry visualization.
The other driver was ultimately found at fault after entering the roadway and colliding with the Tesla while FSD v14.2.2.5 was engaged.
What makes this crash interesting is that there appear to be multiple contributing factors:
• The driver was pressing the accelerator before the collision, causing the vehicle to accelerate to roughly 40 mph. Had the throttle not been overridden, FSD may have approached the area at a lower speed.
• A portion of the striking vehicle was visible between the stopped cars before it fully emerged into the roadway. FSD did not react until the vehicle entered its path, leaving only a few hundred milliseconds to respond.
By the time emergency braking began, there simply wasn’t enough distance left to avoid the collision.
The other driver caused the crash, but it’s an interesting example of how throttle overrides, speed, and anticipation of partially occluded vehicles can all influence the outcome.
@Tesla_AI
64
9
406
61,628
Many doubted my report of a near head-on under Tesla FSD 14.3.3: "no proof FSD was on, no proof your intervention avoided anything."
Turns out Tesla embeds per-frame telemetry inside the dashcam video files themselves (H.264 SEI metadata). I had all 433 frames decoded: speed, steering angle, pedals, GPS, and the automation-engagement flag.
What the data show: • Engaged, zero pedal input, steady 50 mph at night • A red lens-flare "ghost" blooms on the right shoulder; ~0.2 s later the system brakes at 0.9 g and steers LEFT toward the double yellow with an oncoming car ~1 second away • My wheel yank (−5.6°→ 34.6° in 0.3 s) drops the engagement flag mid-maneuver, the exact signature of a steering-override disengagement • At closest approach our left flank was at the centerline as the oncoming sedan passed
On the recorded trajectory, one more second would have resulted in an offset head-on at ~70 mph combined closure. The proof was embedded in the video all along.
I'm happy to share the entire report AMAZINGLY analyzed by Claude Fable 5.
42
11
140
13,109
Also this:
Jun 10
Ok there seems to be about a 27 degree lag from when the wheel is yanked until FSD telemetry logs disengaged state. See wheel yank test below.
This means that @DocBorelli did indeed turn the wheel when FSD was still heading toward the car.
Thanks @DevinOlsenn for pointing this out!
1
2
1,182
Final analysis including the 0.27-0.29 FSD cutoff telemetry lag. It's clear I intervened or FSD would have continued along the path towards a collision.
2
2
613
A. Joseph Borelli, Jr., MD retweeted
Jun 10
Ok there seems to be about a 27 degree lag from when the wheel is yanked until FSD telemetry logs disengaged state. See wheel yank test below.
This means that @DocBorelli did indeed turn the wheel when FSD was still heading toward the car.
Thanks @DevinOlsenn for pointing this out!
1
1
38
5,194
Excerpts from the simply INCREDIBLE Claude Fable 5 analysis:
1
11
1,184
1
1
17
1,092
A. Joseph Borelli, Jr., MD retweeted
🚗 Tesla Robotaxi just registered 10 new robotaxis with the Texas DMV — now 69 in its TX fleet. fsddb.com/robotaxi?operator=…
3
6
135
58,534
Worst FSD critical takeover I've ever had – potentially fatal – and I've been an OG beta tester across multiple vehicles.
On 14.3.3, the car appears to misread round red glare spots as a small animal and jerks hard into oncoming traffic. Had I not intervened, a head-on was likely. Reported as critical.
This is the regression you get when you raise the gain on small-animal detection: a phantom obstacle triggering an evasive swerve into oncoming cars.
Exactly why we still need supervision and why unsupervised FSD for owners will need FSD 15, at least.
@Tesla_AI @aelluswamy @wholemars @SawyerMerritt @AIDRIVR
220
36
717
219,490
Yup
Jun 4
BREAKING: SPLC paid for KKK cross burnings, robes and hoods, recruitment, living expenses, racist merch: explosive new indictment
thepostmillennial.com/splc-p…
1,867
17,555
93,200
25,753,000
Yup
Jun 4
Right-wing extremism is so uncommon that left-wing extremists have to fund it.
2,540
18,531
130,554
13,955,027
A. Joseph Borelli, Jr., MD retweeted
May 30
This seems like the kind of thing that psychiatry (and all of medicine) should get excited about. While there may be various pathways for how sleep-disordered breathing causes/contributes to different psych. disorders, it can't be explained by a simple 1/
researchgate.net/publication…
3
7
20
3,640
A. Joseph Borelli, Jr., MD retweeted
May 24
1. FSD 14.3.3 attempts to pass.
2. FSD see's TRUCK speed limit sign
3. FSD gives up on passing.
4. FSD camps out in the fast lane with people behind me who all now hate me because they can’t get by.
@Tesla_AI - Is this working as designed? This consistently happens in hurry and standard and continues on FSD 14.3.3
31
4
122
20,748
Wow! @Waymo suspends highway drives plus shuts down completely in 3 cities. $TSLA
autoevolution.com/news/waymo…
1
2
271
2
2
231
A. Joseph Borelli, Jr., MD retweeted
May 21
The end of a legend is the beginning of a new dawn. It starts with a mission of a scalable electrified future, and we continue this mission forward.
12
11
298
11,636
