News
SpaceX begins huge dirt pile removal to pave way for BFR spaceship hop tests
After more than two years of silence, SpaceX has taken the first major tangible steps towards the construction of a dedicated South Texas rocket testing facility.
In anticipation of a full-scale BFR spaceship (BFS) hop test campaign that could begin as early as late 2019, local contractors and a smattering of SpaceX employees have begun to earnestly break down and repurpose a large quantity of dirt – known as a surcharge pile – to allow the construction of real facilities to begin.
Documented as of late by a handful of interested local observers and another subset of less local but equally interested followers, SpaceX’s prospective South Texas test and launch facilities have experienced a near-unprecedented burst of activity over the last two months, most notably including the arrival of a small fleet of heavy machinery and construction contractors at a site SpaceX has been working on for three years.
After ~36 months of dead silence, this activity correlates well with recent comments from SpaceX executives Elon Musk and Gwynne Shotwell indicating that the company is still targeting inaugural BFR spaceship hop tests sometime near the end of 2019.
Shotwell: think we’ll be “hopping” the second stage of BFR (the BFS) late next year. #DARPA60
— Jeff Foust (@jeff_foust) September 6, 2018
The infrastructure needed for those early tests could be quite sparse depending on the status of the BFR hardware to be ‘hopped’ – Falcon 9’s Grasshopper and F9R test campaigns, for example, operated off of a tiny concrete pad with extremely minimalist ground support equipment (GSE). Photos from a number of videos SpaceX posted during those crafts’ 2012-2014 series of hop tests demonstrate this minimum well, although chances are good that the company will build up Boca Chica a bit beyond the test pad used for Falcon 9 booster recovery R&D.
-
- F9R seen just before liftoff for a 2014 hop test at SpaceX’s McGregor, TX test facilities. (SpaceX)
-
- Just the bare necessities. (SpaceX)
SpaceX’s Grasshopper and F9R hop tests took place exclusively at the company’s well-established McGregor, Texas testing facilities, offering a range of large hangars, three operational Merlin 1D and Vacuum test bays, and dedicated stands for integrated first and second stage static-fire tests, among countless other rocketry-related amenities. The secluded South Texas coastal region where SpaceX wants to test – if not launch – integrated BFRs has none of McGregor’s preexisting infrastructure, however – anything SpaceX needs will have to be built from scratch on-site.
There is activity. pic.twitter.com/A8JYw6vdW6
— Nehkara (@Nehkara) October 13, 2018
Thus far, almost no real structures have been constructed, aside from a small-ish sheet metal shed that was literally built around a huge crane that arrived on SpaceX property a few months prior. Over the last two or so years, all activity at the South Texas site clustered specifically around a plot where two large radio dishes – and eventually cryogenic storage tanks – were delivered, installed, and/or stored. However, the actual site of the pad SpaceX originally planned to launch Falcon 9 and Heavy from is a mile or two East of that highly visible development, the same location where a flurry of activity has begun in the last month.
-
- A map showing several locations SpaceX planned (as of 2014) to develop.
-
- SpaceX’s proposed launch site (right) and the currently location of radar dishes, a large crane, and several propellant tanks. (Google)
In 2015, SpaceX trucked in several hundred thousand tons of dirt to be packed on top of the site where the company eventually planned to build a large Falcon integration hangar and then left for several years to crush the softer marshlands beneath it into firm submission. That time appears to be up, as the work now ongoing at that site is focused on removing that surcharging dirt now that the soil beneath it is stable enough to host heavy, long-term structures like a rocket launch pad.
Most of that massive dirt pile will likely remain at SpaceX’s South Texas property, to be used as a basic construction material as the company begins to build some semblance of the facility described in its approved 2014 environmental impact assessment. As it takes shape, it will become clear just how closely SpaceX is sticking to those original plans. BFR hop tests could begin by late 2019 if prototype spaceship construction – already in work at a tent in Port of Los Angeles – proceeds smoothly.
For prompt updates, on-the-ground perspectives, and unique glimpses of SpaceX’s rocket recovery fleet check out our brand new LaunchPad and LandingZone newsletters!
Tesla’s Head of AI, Ashok Elluswamy, says that something that was expected with version 14.3 of the company’s Full Self-Driving platform has already partially shipped with the current build of version 14.2.
Tesla and CEO Elon Musk have teased on several occasions that reasoning will be a big piece of future Full Self-Driving builds, helping bring forth the “sentient” narrative that the company has pushed for these more advanced FSD versions.
Back in October on the Q3 Earnings Call, Musk said:
“With reasoning, it’s literally going to think about which parking spot to pick. It’ll drop you off at the entrance of the store, then go find a parking spot. It’s going to spot empty spots much better than a human. It’s going to use reasoning to solve things.”
Musk said in the same month:
“By v14.3, your car will feel like it is sentient.”
Amazingly, Tesla Full Self-Driving v14.2.2.2, which is the most recent iteration released, is very close to this sentient feeling. However, there are more things that need to be improved, and logic appears to be in the future plans to help with decision-making in general, alongside other refinements and features.
On Thursday evening, Elluswamy revealed that some of the reasoning features have already been rolled out, confirming that it has been added to navigation route changes during construction, as well as with parking options.
He added that “more and more reasoning will ship in Q1.”
🚨 Tesla’s Ashok Elluswamy reveals Nav decisions when encountering construction and parking options contain “some elements of reasoning”
More uses of reasoning will be shipped later this quarter, a big tidbit of info as we wait v14.3 https://t.co/jty8llgsKM
— TESLARATI (@Teslarati) January 9, 2026
Interestingly, parking improvements were hinted at being added in the initial rollout of v14.2 several months ago. These had not rolled out to vehicles quite yet, as they were listed under the future improvements portion of the release notes, but it appears things have already started to make their way to cars in a limited fashion.
Tesla Full Self-Driving v14.2 – Full Review, the Good and the Bad
As reasoning is more involved in more of the Full Self-Driving suite, it is likely we will see cars make better decisions in terms of routing and navigation, which is a big complaint of many owners (including me).
Additionally, the operation as a whole should be smoother and more comfortable to owners, which is hard to believe considering how good it is already. Nevertheless, there are absolutely improvements that need to be made before Tesla can introduce completely unsupervised FSD.
Elon Musk
Tesla’s Elon Musk: 10 billion miles needed for safe Unsupervised FSD
As per the CEO, roughly 10 billion miles of training data are required due to reality’s “super long tail of complexity.”
Tesla CEO Elon Musk has provided an updated estimate for the training data needed to achieve truly safe unsupervised Full Self-Driving (FSD).
As per the CEO, roughly 10 billion miles of training data are required due to reality’s “super long tail of complexity.”
10 billion miles of training data
Musk comment came as a reply to Apple and Rivian alum Paul Beisel, who posted an analysis on X about the gap between tech demonstrations and real-world products. In his post, Beisel highlighted Tesla’s data-driven lead in autonomy, and he also argued that it would not be easy for rivals to become a legitimate competitor to FSD quickly.
“The notion that someone can ‘catch up’ to this problem primarily through simulation and limited on-road exposure strikes me as deeply naive. This is not a demo problem. It is a scale, data, and iteration problem— and Tesla is already far, far down that road while others are just getting started,” Beisel wrote.
Musk responded to Beisel’s post, stating that “Roughly 10 billion miles of training data is needed to achieve safe unsupervised self-driving. Reality has a super long tail of complexity.” This is quite interesting considering that in his Master Plan Part Deux, Elon Musk estimated that worldwide regulatory approval for autonomous driving would require around 6 billion miles.
FSD’s total training miles
As 2025 came to a close, Tesla community members observed that FSD was already nearing 7 billion miles driven, with over 2.5 billion miles being from inner city roads. The 7-billion-mile mark was passed just a few days later. This suggests that Tesla is likely the company today with the most training data for its autonomous driving program.
The difficulties of achieving autonomy were referenced by Elon Musk recently, when he commented on Nvidia’s Alpamayo program. As per Musk, “they will find that it’s easy to get to 99% and then super hard to solve the long tail of the distribution.” These sentiments were echoed by Tesla VP for AI software Ashok Elluswamy, who also noted on X that “the long tail is sooo long, that most people can’t grasp it.”
News
Tesla earns top honors at MotorTrend’s SDV Innovator Awards
MotorTrend’s SDV Awards were presented during CES 2026 in Las Vegas.
Tesla emerged as one of the most recognized automakers at MotorTrend’s 2026 Software-Defined Vehicle (SDV) Innovator Awards.
As could be seen in a press release from the publication, two key Tesla employees were honored for their work on AI, autonomy, and vehicle software. MotorTrend’s SDV Awards were presented during CES 2026 in Las Vegas.
Tesla leaders and engineers recognized
The fourth annual SDV Innovator Awards celebrate pioneers and experts who are pushing the automotive industry deeper into software-driven development. Among the most notable honorees for this year was Ashok Elluswamy, Tesla’s Vice President of AI Software, who received a Pioneer Award for his role in advancing artificial intelligence and autonomy across the company’s vehicle lineup.
Tesla also secured recognition in the Expert category, with Lawson Fulton, a staff Autopilot machine learning engineer, honored for his contributions to Tesla’s driver-assistance and autonomous systems.
Tesla’s software-first strategy
While automakers like General Motors, Ford, and Rivian also received recognition, Tesla’s multiple awards stood out given the company’s outsized role in popularizing software-defined vehicles over the past decade. From frequent OTA updates to its data-driven approach to autonomy, Tesla has consistently treated vehicles as evolving software platforms rather than static products.
This has made Tesla’s vehicles very unique in their respective sectors, as they are arguably the only cars that objectively get better over time. This is especially true for vehicles that are loaded with the company’s Full Self-Driving system, which are getting progressively more intelligent and autonomous over time. The majority of Tesla’s updates to its vehicles are free as well, which is very much appreciated by customers worldwide.
Tesla AI Head says future FSD feature has already partially shipped
Tesla’s Elon Musk: 10 billion miles needed for safe Unsupervised FSD
