Evan Coons (@evan_coons) header
Evan Coons (@evan_coons) profile picture

π”Šπ”¬π”±π”₯ 𝔄𝔫𝔀𝔒𝔩 ֆ𝔦𝔫𝔫𝔒𝔯 0_-β˜ οΈπŸ‘»πŸ˜‡

Joined March 2015
Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)Photo by Evan Coons (@evan_coons)
Communist Control Act of 1954 50 USC CHAPTER 23, SUBCHAPTER IV: COMMUNIST CONTROL uscode.house.gov/view.xhtml?…
8
2
1
44
20,328
With this tech, Tesla can build better than lidar level HD maps of the entire world using fleet gathered data
39
20
10
950
23,066
Evan Coons retweeted
Make your girl to get some cardio in so she doesn’t get fat ❀️
206
2,031
106
61,898
1,068,648
Evan Coons retweeted
Replying to @ElleRen7
You ask us to move mountains! Very well, we shall.
184
143
30
1,925
85,015
Evan Coons retweeted
Replying to @SmokeAwayyy
Tesla real-world AI will increase in intelligence by about an order of magnitude per year
266
506
67
7,446
179,487
Evan Coons retweeted
Replying to @BLKMDL3 @wholemars
In case anyone is curious: We’ve had a ~pixel-perfect world model since last year, which is critical for synthetic data generation. The (much) smaller version of that in the car is a conditional mean-flow model, based on the recent sequence of Tesla Universal Vision Encoder features, which are the same ones that are plugged into the 3B encoder model that produces the driving actions. We fork off from these UVE features, then run a separate ~1B diffusion model. This takes in the previous reality-view generation with added noise and then denoises it to the current visualization. It then produces a small video chunk (8 images at 36 fps, at the resolution of the UI screen). This work is done by 1/2 of a TRIP engine every UVE frame at 18 hz and is spread over 4 cycles. Currently, the latency is a bit high due to compute constraints, but we have ways to interleave newer UVE features along the diffusion transformer layers to cut roughly 35% of the latency.
653
1,141
377
15,333
1,233,521
Evan Coons retweeted
Some people thought we meant 25% improvement, no we mean 25 times! Welcome to the singularity. Hope you’re enjoying your stay.
FSD V15 is 25x safer than V14 I would have guessed V14 is at MINIMUM 2x safer than a human (probably more). These numbers are getting insane. Singularity is here.
1,711
3,364
413
37,695
2,380,239
Evan Coons retweeted
Replying to @elonmusk
2
9
74
22,129
Evan Coons retweeted
This is not a brothel selecting prostitutes; this place is China’s Great Hall of the People selecting servers β€” it's where top CCP officials to host general assembly or annual convention.
154
482
60
2,591
327,494
Evan Coons retweeted
It’s high time we probed Uranus again! Much better images are needed (actually).
6,825
4,640
1,079
74,040
7,110,479
Evan Coons retweeted
"We definitely want our rocket to reach Uranus. It's a streach goal to reach Uranus." δΈ€ Elon Musk
It’s high time we probed Uranus again! Much better images are needed (actually).
185
256
41
1,585
58,425
Evan Coons retweeted
The crazier thing is that the right side uses less compute than what the left used to take. Extreme compute efficiency optimization.
Look how far we’ve come
830
1,376
291
15,882
1,650,222
Evan Coons retweeted
This is NUTS. It goes around a Huge Branch in the Road v15
251
632
188
9,014
3,364,818
POV using FSD v15 driving to Banff πŸ€€β„οΈβ„οΈβ„οΈ
27
41
15
748
46,138
Evan Coons retweeted
FSD V15 IS AMAZING
63
182
68
2,781
280,493
Evan Coons retweeted
Taking Tesla FSD V15 on the highway. Love all the floating arrows lol
289
492
131
6,498
1,271,217
Evan Coons retweeted
Look how FSD V15 shows all the Christmas lights/decorations.
142
264
54
4,095
329,629
Evan Coons retweeted
Tesla FSD 15’s visualizer looks just like GTA 6 in real time. 🀯
70
135
16
1,000
48,577
Evan Coons retweeted
Replying to @TeslaSI
Huge progress
2
9
3
154
11,348
Full release notes below – – – v15 upgrades every part of the end-to-end driving network. Includes: Upgraded vision encoder shared between FSD, Robotaxi, and Optimus, which is trained on millions of internet videos for improved generalization and data efficiency, improving the critical intervention rate by 25x. Introduced Tesla Reality View, replacing all of the explicit model signals into a single end-to-end visualization using less total compute. Improved navigation by using an end-to-end learned model based on route preference data from the fleet. Improved parking location selection by using personalized parking history, and the map will now display multiple parking options at your destination. Improved driver monitoring by increasing vision-based attention monitoring availability with hats and sunglasses and decreasing strictness in higher speed driver profiles. Improved detection of road signs, small animals, road debris, and chains. Improved detection of potholes, road details, and avoidance of deep standing water. Improved speed handling for each driver profile, school zones and speed limits, and inclement weather. Improved Autoshift functionality by unifying with FSD-based gear predictions.
FSD v15 now starting to roll out – upgrading every part of the end-to-end driving network Safety 25x better handling of safety critical cases Tesla Reality ViewΒ  Adds a live visualization of the drive that lets you see & control what FSD is planning to do Navigation for start & end of the trip now learns end-to-end from fleet route preferences. Later v15 releases will expand this to the entire route. You also should notice better detection of signs, animals, debris, potholes and standing water, plus more natural speed handling in school zones and inclement weather. Lastly, FSD can now slow for speed cameras & Bike Rack Mode lets you enable FSD w/ bike racks or similar hitch accessories
335
825
190
7,686
1,326,911
Evan Coons retweeted
Tesla FSD V15 is a banger release! Completely new architecture that deserves being called β€œsuper” intelligence, as it drives better than human intelligence.
Full release notes below – – – v15 upgrades every part of the end-to-end driving network. Includes: Upgraded vision encoder shared between FSD, Robotaxi, and Optimus, which is trained on millions of internet videos for improved generalization and data efficiency, improving the critical intervention rate by 25x. Introduced Tesla Reality View, replacing all of the explicit model signals into a single end-to-end visualization using less total compute. Improved navigation by using an end-to-end learned model based on route preference data from the fleet. Improved parking location selection by using personalized parking history, and the map will now display multiple parking options at your destination. Improved driver monitoring by increasing vision-based attention monitoring availability with hats and sunglasses and decreasing strictness in higher speed driver profiles. Improved detection of road signs, small animals, road debris, and chains. Improved detection of potholes, road details, and avoidance of deep standing water. Improved speed handling for each driver profile, school zones and speed limits, and inclement weather. Improved Autoshift functionality by unifying with FSD-based gear predictions.
1,372
2,012
255
20,399
1,468,546