Join Ghost CEO @ghosthayes and @PureStorage Field CTO @bitdisturbance for today’s webinar discussing how data drives the AI development pipeline for software defined vehicles: today at11AM PST!

Ghost founder/CEO @ghosthayes on @Forbes - The Next Trillion-Dollar Car Company Will Have An API.

And for a deeper take on how Large Models will impact autonomy, read @GhostAutonomy model engineer @PrannayKhosla’s take:

Watch how MLLMs reason about intersections, understand construction scenes, and interpret urban road environments:

We believe that MLLMs will have a profound impact on the autonomy software stack, with the potential power to reason about driving scenes holistically to provide AVs deeper understanding and guidance on the correct driving maneuver by considering the scene in totality.

We’re excited to announce that @OpenAI Startup Fund has invested in @GhostAutonomy to Bring Multi-modal LLMs to Autonomous Driving

Find the session and details here:

Attending @Reuters AutomotiveUSA in Detroit next week? Hear Ghost CEO @ghosthayes and @PureStorage CTO Michael Cornwell discuss AI, LLMs, and the data pipelines that underlie building the self-driving software stack.

Tunnels present particular challenges to AV systems - rapid camera exposure changes, narrow lanes, and unique radar reflections (not to mention no GPS!). Watch Ghost validate tunnel handling in the Caldecott Tunnel in Berkeley - one of the toughest tunnels in the Bay Area!

"Any very complex computer science problem is being subject to AI, and with AI you almost always get better performance.". @ghosthayes presentation on making AI reliable for autonomous driving. Video and full transcript here:

How does Fusion turn noisy sensor outputs into a clear view of obstacles and the scene? In this episode of Talking Autonomy, Model Engineer @PrannayKhosla breaks down Ghost’s approach to late fusion of vision and radar.

Humans don’t need HD Maps - so why should AVs? In this episode of Talking Autonomy, learn how Ghost drives without the fragile crutch of HD Maps:

Ghost continues to validate generalization by testing the Ghost Autonomy Engine in more and more places! In this video you'll see Ghost's first drive in Canada, taking the King's Highway 401 to Toronto - a road we’ve never driven or been trained on before.

Ever wonder how Ghost’s AI software scales to everyday consumer cars? Check out this episode of Talking Autonomy with Ghost hardware engineer @ArpitaGD to understand the Ghost reference hardware stack. <$1,500 and 150W - how’s it possible?.

RT @GuyDealership: RAISED $230M FOR AUTONOMOUS VEHICLES 🚘 . – How Ghost is different than Tesla .– When you’ll actually stop paying attenti….

We're now in Detroit! Thank you @BreanaCNoble for riding with us. "Autonomy is going to happen. and it's not just going to happen in San Francisco and Phoenix. It's going to actually happen for you and your car at a price that everybody can afford.".

Read more about why generalization is hard, and the Ghost technologies that enable generalization in our blog:

Engineering for generalization is hard, but critical to Ghost’s mission to make self-driving mainstream in everyday consumer cars. Our choices of universal AI (vs. image recognition), no HD-Maps, and fully auto-labeled training data all enable rapid generalization.

What happens when a self-driving car drives on a road it's never seen before? Watch Ghost drive to Vegas for the first time. 140 miles, 2+ hours, average 71mph, no safety driver interventions. Full video here:

Speaking of Canada, @GhostAutonomy CEO @ghosthayes will be speaking Thursday, 12:05 EST at #CollisionConf in Toronto! Be sure to check him out if you are an attendee!.