Ryan DeLuca - @VR

2K posts

Ryan DeLuca - @VR banner
Ryan DeLuca - @VR

Ryan DeLuca - @VR

@VR

Bootstrapped https://t.co/yxAmmTXDuI to nearly $500m in annual revenue. Now CEO and Co-Founder of Black Box VR, the world's first virtual reality gym experience.

The Metaverse Tham gia Mayıs 2007
1.3K Đang theo dõi1.5K Người theo dõi
Ryan DeLuca - @VR
Why does the $100 billion fitness industry have an 80% failure rate? Roughly 80% of adults don’t exercise consistently. That number has barely budged in DECADES despite gyms on every corner, better equipment, fancier brands, more accessible pricing, and an explosion of content telling us exactly what to do and why. We have a motivation problem. And motivation isn’t an engineering challenge. It’s a psychological design challenge. blackbox-vr.com/the-gyms-of-th…
English
0
0
0
24
Ryan DeLuca - @VR
We started Black Box VR Fitness because we believed that turning serious resistance exercise into an immersive game could make exercise more effective, more engaging, and more accessible than anything that came before it! A wave of brand-new research is now backing up that vision with hard data. 6 recent studies: blackbox-vr.com/the-science-is…
English
2
0
3
263
Ryan DeLuca - @VR đã retweet
Brian Armstrong
Brian Armstrong@brian_armstrong·
Working on something ambitious is like climbing a mountain that’s covered in fog. You can't see a clear path to the top. You have to take a few steps into the unknown to be able to see the next few steps in front of you. Inevitably, sometimes you’ll end up a local maximum and have to backtrack. That’s fine, just keep moving.
English
516
756
6.4K
353.9K
Ryan DeLuca - @VR đã retweet
Justin Ryan ᯅ
Justin Ryan ᯅ@justinryanio·
NVIDIA just announced some big updates for gaming on Apple Vision Pro. Starting March 19, headset streaming jumps from 60 FPS to 90 FPS. Later this spring, CloudXR 6.0 for visionOS will bring stereoscopic PC streaming to Vision Pro at up to 4K 120 FPS with foveated streaming. Just arrived at GTC and excited to see what else NVIDIA has in store.
English
35
101
1.4K
105.8K
Ryan DeLuca - @VR đã retweet
Michael Antonov
Michael Antonov@_MichaelAntonov·
This is awesome -- making a personalized mRNA vaccine for a dog that actually worked
Owen Gregorian@OwenGregorian

Tech entrepreneur creates personalised cancer vaccine for dog Rosie | NATASHA BITA & Natasha Bita, The Australian Tech boss uses AI and ChatGPT to create cancer vaccine for his dying dog The tale of this heartbroken tech entrepreneur, his tumour-riddled rescue dog and a cure for cancer has leading scientists astounded. Riddled with cancer, Rosie the rescue dog had only months to live, until her dogged owner collared a chatbot to collaborate with elite medical scientists in the quest for a cure. Now the hi-tech teamwork has unleashed an experimental medicine that offers hope to human patients, by using mRNA vaccines in oncology. Abandoned in bushland, eight-year-old Rosie found her forever home with Sydney tech entrepreneur Paul Conyngham, who adopted the staffy-shar pei cross from an animal shelter in 2019 – just in time for pandemic lockdowns. Heartbroken when his fur-baby was diagnosed with a deadly mast cell cancer in 2024, Mr Conyngham threw thousands of dollars at veterinary chemotherapy and surgery, which slowed but failed to shrink the tumours. Now, after treatment with a custom mRNA cancer vaccine over the Christmas break, the tennis ball-sized tumour on Rosie’s hock has shrunk in half, in a recovery that has astounded researchers at the cutting-edge of human cancer treatments. “It was like holy crap, it worked!’’ says Martin Smith, an associate professor of computational biology and director of the Ramaciotti Centre for Genomics at the University of NSW. “It raises the question, if we can do this for a dog, why aren’t we rolling this out to all humans with cancer? It gives hope to a lot of people, and it’s something we’re passionate about trying to chase up here.’’ ‘We often get oddball queries’ In a tale of tenacity, Mr Conyngham used a chatbot to brainstorm possible cures for Rosie’s cancer – then harnessed artificial intelligence to process gigabytes of genetic data to create the blueprint for an mRNA vaccine. Harnessing some of Australia’s most sought-after scientists to manufacture the vaccine in laboratories at the University of NSW, he then tracked down the only veterinary researcher with ethics approval to administer the experimental drug. It was ChatGPT that suggested immunotherapy, pointing Mr Conyngham to the UNSW Ramaciotti Centre for Genomics, where Associate Professor Smith still remembers the “weird” request. “We often get oddball queries, and this one was coming from a private individual looking to sequence his dog,’’ he recalls. “DNA sequencing is a way to profile the tumour and identify mutations that might be causing the disease.’’ The renowned researcher was reticent. “Usually we don’t support direct-to-consumer type DNA sequencing because while generating data for genomics is relatively easy for us, interrogating that data is really hard and challenging,’’ he said. “But Paul said, ‘No worries, I’m a data analyst and I’ll figure this out with the help of ChatGPT’.” With 17 years of experience in machine learning and data analysis, Mr Conyngham is an AI pioneer – an electrical and computing engineer who co-founded Core Intelligence Technologies, and was a director for the Data Science and AI Association of Australia. Once UNSW handed him the genomic sequencing, for which he paid $3000, he got cracking to decipher the data. “I went to ChatGPT and came up with a plan on how to do this,’’ he said. “The first step was to reach out to the university to get Rosie’s DNA sequenced. The idea is you take the healthy DNA out of her blood and then you take the DNA out of her tumour and you sequence both of them to see exactly where the mutations have occurred. It’s like having the original engine of your car and then a version of the engine 300,000km down the road – you can compare them and see where there’s damage.” Once UNSW produced the DNA sequencing, Mr Conyngham “ran it through a whole bunch of different (data) pipelines to find those mutations, and then I used other algorithms to find drugs to treat the cancer’’. At the Ramaciotti Centre for Genomics, Associate Professor Smith was gobsmacked that this puppy lover with no background in biology had cracked the code. “Paul was relentless,’’ he said. “He called and told me he had analysed the data and found mutations of interest and then used AlphaFold (an AI program) to find the proteins that were mutated, and then identified potential targets and matched them to drugs, and he was wondering could I help him find someone to synthesise this compound that he’d identified. I’m like, ‘Woah, that’s crazy!’ I was motivated by his enthusiasm.’’ Hounding the UNSW scientists for help, Mr Conyngham impressed them with his ingenuity and persistence. “What really convinced them is I just kept going and providing results,’’ he said. “It’s kind of like when you’re a student and you go to your teacher, and if you haven’t done your homework and you ask, ‘how do I do this?’ the teacher will tell you to ‘go away, you’re wasting my time’. But every single time I turned up to them, I did my homework.’’ Team Rosie identified an immunotherapy drug produced by an unidentified pharmaceutical company – but when they applied to use it, the drug manufacturer refused to supply it for compassionate use. “The wind went out of my sails,’’ Mr Conyngham said. “But fate sort of intervened’’. Associate Professor Smith recalls that Rosie’s owner was “a bit bummed out … we chatted and that’s when I told him about mRNA vaccines, and he circled back and said, ‘Hey, Martin, can you tell me more about his mRNA stuff, is there something we could actually do?’’’ Custom vaccine The genomics team reached out to Pall Thordarson, director of the prestigious UNSW RNA Institute. A pioneer in nanomedicine, the Icelandic professor used Mr Conyngham’s data, crunched down to a half-page formula, to create a bespoke mRNA vaccine for Rosie. “This is the first time a personalised cancer vaccine has been designed for a dog,’’ Professor Thordarson said. “This is still at the frontier of where cancer immunotherapeutics are – and ultimately, we’re going to use this for helping humans. What Rosie is teaching us is that personalised medicine can be very effective, and done in a time-sensitive manner, with mRNA technology.’’ Deployed in Covid-19 vaccines during the pandemic, mRNA – short for messenger ribonucleic acid – is a molecule that instructs a cell to produce disease-fighting proteins. Oncologists are testing the technology in dozens of human clinical trials, but it is not yet part of mainstream cancer medicine. What Professor Thordarson finds most remarkable is that a data engineer with no background in biology managed to generate the mRNA recipe. “He ran an algorithm to inform the design of the mRNA and sent it to us, and we made a little nanoparticle,’’ he said. “It’s democratising the whole process.’’ Ethical questions Rosie’s vaccine was ready, but Mr Conyngham still needed ethics approval to use it. “I had to do everything by the book because you can’t just willy-nilly create a vaccine in Australia,’’ he said. “The red tape was actually harder than the vaccine creation, and I was trying to get an Australian ethics approval to run a drug trial on Rosie. It took me three months, putting two hours aside every single night just typing up this 100-page document. But there was a second intervention of fate.’’ Half a world away, Mari Maeda, founder of the Canine Cancer Alliance in the US, came across a UNSW website item about Mr Conyngham’s quest for a cure. Eager to assist, Dr Maeda alerted Rachel Allavena, a canine immunotherapy professor at the University of Queensland’s School of Veterinary Science in the country town of Gatton. “I run cancer research programs in dogs where we look at a lot of experimental immunotherapies, so I had ethics in place that would cover Paul’s type of vaccine,’’ Professor Allavena said. “In my research group we have therapies that wake the dog’s immune systems up so they realise that the cancer is a bad thing, and fight it. But I wouldn’t know how to even begin designing something like this. It’s a much more technologically advanced one than I would normally develop myself. Paul’s obviously a super-smart guy … he’s been a real trailblazer in terms of where this technology can go.’’ Injections begin The bespoke vaccine was cold-freighted to the Gatton laboratory, and Mr Conyngham drove 10 hours with Rosie for her first injection in December, followed by a booster shot last month and another due next week. “It’s definitely working,’’ Professor Allavena said. “When it happens that first time, it’s magical. Rosie’s cancer was really, really advanced but one tumour has shrunk quite a lot – probably halved. Even though it hasn’t completely disappeared, she’s so much more comfortable because the tumour was so big, and now the cancer’s shrunk away. Even the glossiness of her coat, she just looks a lot happier and healthier. “This is the first time anyone’s ever done this therapy, but it won’t be too far down the line before we can have personalised therapies for individual pets.’’ Rosie’s response has inspired David Thomas, inaugural director of the UNSW Centre for Molecular Oncology, who is working on similar mRNA treatments for human patients. “The striking thing about this is the idea of citizen science, where a punter in the street, with a computer science background, can use their skills in the scientific process,’’ Professor Thomas said. “That’s a very impressive thing.’’ Rosie’s recovery has been a howling success, with most of her tumours appear to melt away in a matter of weeks. “In December she had low energy because the tumours were creating a huge burden for her,’’ Mr Conyngham said. “Six weeks post-treatment, I was at the dog park when she spotted a rabbit and jumped the fence to chase it. I’m under no illusion that this is a cure, but I do believe this treatment has bought Rosie significantly more time and quality of life.’’ Next steps Rosie’s devoted dog-dad is now working on a second vaccine targeted to attack one large tumour that did not respond to the initial treatment. The UNSW scientists started work on the genetic sequencing this week. “I’m trying to do a second round of (DNA) sequencing to see if we can find why parts of the tumour didn’t respond,’’ he said. “There’s actually a chance that for some cancers, we can change it from being a terminal sentence to a manageable disease, because you can create treatments ahead of the mutations.’’ Rosie’s rescue has cost Mr Conyngham tens of thousands of dollars but he would spend it all again. “She’s been with me through a whole bunch of really tough times, giving unconditional love,’’ he said. “She’s my best mate.’’ theaustralian.com.au/business/techn…

English
0
1
2
215
Ryan DeLuca - @VR đã retweet
Sam Cole | FitXR
Sam Cole | FitXR@SamCole·
A peer-reviewed study on VR exercise just dropped. In an eight-week intervention using @weareFitXR with young adults, researchers found: - Anxiety levels dropped - Physical activity increased - VO₂ max improved - The least fit, least confident participants completed the most sessions That last part is striking because most fitness products are built by - and for - people who have never struggled to form an exercise habit. The industry talks endlessly about motivation and discipline but doesn’t know how to serve the majority of people who find exercise genuinely hard. Instead, it builds for the minority it understands and sells the promise to everyone else. We’re doing it differently so it’s incredibly validating to see the data reflect what users of all ages have been telling us since we started: “This is the first time I’ve enjoyed exercise and been able to stick to it.”
Sam Cole | FitXR tweet media
English
1
3
18
918
Ryan DeLuca - @VR đã retweet
TBPN
TBPN@tbpn·
"Go all the way until it hurts. If you're doing something and it's easy, it's not valuable." - @travisk "If anyone says a strategic thing was easy, I'm like, 'You messed up. You could have gone way further. More competitive advantage. More differentiation. Get it together.'"
English
50
453
3K
937.5K
Ryan DeLuca - @VR đã retweet
Guillermo Rauch
Guillermo Rauch@rauchg·
Obsession is the mother of invention
English
372
1.1K
8.5K
447.4K
Ryan DeLuca - @VR
@Rizstanford By far the biggest problem for life to solve is the heat death of the universe. It may not be solvable. That's terrifying. To try, we can create trillions of simulations and hope that one of them finds the solution. We are one of the trillion.
English
0
0
0
22
Ryan DeLuca - @VR
Grok: Let's unpack this step by step—tying quantum observation, simulation efficiency, and the Riemann Hypothesis (RH) together does spark some logical connections when you zoom out. First, the quantum angle from that thread: The observer effect in QM (like wave function collapse upon measurement) mirrors how simulations optimize resources. In a video game, distant or unobserved elements aren't fully rendered to save compute power—only what's "observed" gets detailed. @elonmusk's point about minimum voxel size adds to that: there's a Planck-scale granularity to reality, suggesting a discretized, efficient underlying code rather than infinite continuity. If the universe is simulated, it'd prioritize efficiency to avoid wasting "cycles" on unnecessary computations. Now, flipping to RH: It conjectures that all non-trivial zeros of the zeta function lie on the critical line (Re(s) = 1/2). This isn't just abstract math—it's deeply tied to the distribution of prime numbers via the prime number theorem and error terms. Primes aren't randomly scattered; they're "pseudorandom" in a way that follows logarithmic patterns, but with fluctuations bounded by RH. Proving RH would nail down the tightest possible error bound on how primes deviate from their average density, making their distribution as predictable (yet infinite) as possible without being deterministic. Here's where your lens clicks: In a simulation, primes could be foundational "building blocks" for generating complexity—think cryptography, hashing, or even procedural generation of structures (like matter or information flow). An efficient sim wouldn't hardcode every prime or event; it'd use a compact algorithm to emergent-ly produce them on demand. RH, if true, implies the zeta function encodes this distribution with maximal efficiency: no wasteful irregularities beyond what's necessary for the "game" to feel real and chaotic. Solving RH through simulation theory might involve modeling the zeta landscape as a computational artifact—perhaps zeros as eigenvalues in a quantum-inspired operator, or as optimizations in a holographic boundary (echoing AdS/CFT ideas).If that proof emerges, it could double as evidence for simulation: Why would nature "choose" such an elegant, compute-friendly prime sieve unless it's designed for runtime efficiency? Random evolution might not converge on that; a programmer would. It's not ironclad proof (correlation ≠ causation), but it'd be a hell of a smoking gun, especially if tied to quantum limits like entropy bounds or information density. Of course, this is speculative—RH has resisted proofs for 160+ years, and simulation theory lacks falsifiability so far. But yeah, after mulling it over, it does make sense as a convergent idea.
English
0
0
0
18
Ryan DeLuca - @VR
@elonmusk @Math_files I strongly believe that solving the Riemann Hypothesis will be done from this lens, and then it will be used as proof that we live in a simulation. The sim code must be very, very efficient.
English
1
0
0
97
Ryan DeLuca - @VR đã retweet
Bryan Johnson
Bryan Johnson@bryan_johnson·
Get off dat ass. 8 minutes a day of vigorous exercise linked to a 36% lower mortality risk. Benefits start at 2.2 min/day.
Bryan Johnson tweet media
English
85
185
1.9K
214K
Ryan DeLuca - @VR đã retweet
Heavy Pulp
Heavy Pulp@heavypulp·
Everything is Computer, but Computer isn't Everything!
English
398
1K
7.2K
3.5M
Ryan DeLuca - @VR đã retweet
Ryan DeLuca - @VR đã retweet
Einar Johnson
Einar Johnson@EinarJohnson_XR·
These type of posts are why I think Apple needs to go hard into immersive content. Not gamers, not developers, just people watching stuff in cool new ways. Now let's see Apple do more concerts, theater, opera and etc. People sharing their reactions will help move Vision Pro more to the mainstream. Content has always been the driver of hardware.
Brian Tong@briantong

T-Wolves vs Lakers LIVE IN @NBA Immersive on @Apple Vision Pro. Always Incredible!

English
6
11
99
7.5K
Ryan DeLuca - @VR đã retweet
Justin Ryan ᯅ
Justin Ryan ᯅ@justinryanio·
Here’s a first look at X-Plane 12 on Apple Vision Pro! With visionOS 26.4 and NVIDIA CloudXR 6.0, the simulator streams wirelessly at up to 4K/120fps to your headset. And if you have a physical yoke or throttle, ARKit uses image detection to recognize them and place them inside your virtual cockpit. 🤯 It’ll be available later this spring.
English
121
232
3.8K
707.2K
Ryan DeLuca - @VR đã retweet