Edward Ahn

789 posts

Edward Ahn banner
Edward Ahn

Edward Ahn

@edwardahn9

building 3D conversations that feel in-person • ex- Vision Pro • cmu alum

San Francisco, CA Katılım Haziran 2020
809 Takip Edilen1.1K Takipçiler
Sabitlenmiş Tweet
Edward Ahn
Edward Ahn@edwardahn9·
If you like 3D graphics, I wrote a high-level post on the difference between Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS). It's a ten min read, and aims to educate those not as familiar with the field of neural rendering. Link and some snippets below. 1/5
Edward Ahn tweet media
English
9
85
533
74.3K
John Dagdelen
John Dagdelen@jmdagdelen·
Ready Player Me going under really left a huge vacuum in the XR space. Now that Meta Avatars SDK is at end of development too, I think there’s a fairly big business that can be built serving devs who need a decent cross-platform avatar system. AI could really accelerate this.
English
17
2
71
3.8K
Edward Ahn
Edward Ahn@edwardahn9·
agreed. my AR glasses will always have a place in my life, but as an accessory, not a replacement, to the phone phones never replaced computers so why should glasses replace phones?
Ben Springwater@benspringwater

There is no successor to the smartphone. It's the terminal form factor. Much like the car is the terminal form factor for human transportation. Tesla has improved 1000x over the Model T but you still have the same cab riding on four wheels, because it's the optimal solution given the jobs to be done and constraints of reality. The smartphone has the most intense product market fit of any product ever for a reason: a computer you carry in your pocket and hold in your hand, with a screen you manipulate with your fingers, cannot be meaningfully improved upon for the jobs people want done. This doesn't mean there's not room for awesome new devices, especially with AI opening up new vistas. We have motorcycles, mopeds, scooters, e-bikes, and those funny one-wheeled vehicles you see whizzing through Golden Gate Park. We will have smart glasses, pendants, pucks, and whatever device Hark has in store. Hark seems like an S-tier team with an amazing vision, and I will probably buy their product. Moreover, I wouldn't want to live in a world where crazy ambitious visions aren't pursued with convert's zeal. Nevertheless, I'm writing this because every time I see a venture that explicitly or implicitly promises to supersede the smartphone, I think the same thing: It wouldn't matter if Jony Ive teamed up with the ghost of Steve Jobs and raised an army of the greatest HCI designers that ever walked the earth. It's structural. The smartphone is terminal.

English
1
0
6
345
Alex Konrad
Alex Konrad@alexrkonrad·
Hey folks! If you’re a deep tech / defense founder or VC with thoughts on the implications of the weekend’s DoW actions for your startup or others, I’d love to chat with you. DM or message akonrad.212 on Signal 👋
English
6
3
70
7.9K
Patrick | Megapot
Patrick | Megapot@Patrick_Lung·
@edwardahn9 This was quite the read. Takes a ton of guts and self awareness, thanks for publishing!
English
1
0
1
7
Edward Ahn
Edward Ahn@edwardahn9·
@arampell maybe im on the internet too much if I kept reading "slow boil" and "fast boil" companies as "slow boi" and "fast boi" companies and I didn't question it
English
0
0
2
239
Edward Ahn retweetledi
Zhiwen(Aaron) Fan
Zhiwen(Aaron) Fan@zhiwen_fan_·
InstantSplat++ is now open source. It is a lightweight library that connects foundation models (VGGT, MASt3R, MAP-Anything, etc.) with the Gaussian splatting family. Given uncalibrated images, it optimizes a 3D scene in a few seconds. Try the demo and code here: github.com/phai-lab/Insta…
English
7
90
717
31.4K
Peter Hague
Peter Hague@peterrhague·
One technology that I really wanted to take off, but hasn't, is VR. I mean, I was a teenager the first time around, when the devices used CRTs and you needed a strong neck. Played the bird game in the arcades. The graphics on these devices was very naff. But modern devices (like the Meta Quest 3) which I own are fine. They are light weight, good image quality, decent passthrough for XR and responsive. But for some reason they don't seem to have evolved beyond toys. I've tried using them for serious 3D visualisation as part of my workflow, but its quite clunky to get them to do that. There seem a lot of barriers to development. What happened?
Peter Hague tweet media
English
163
9
218
20.6K
Edward Ahn
Edward Ahn@edwardahn9·
thanks for your thoughts, I actually agree with you you could be right, the real problem is lack of access to inputs or internals that fundamentally make XR so different from other mediums. eg. it is definitely wild that it took this long to access cameras when the entire platform is about how we're blending real world with the virtual and yeah I don't think the UX is fully explored yet either. eg. hand tracking on the AVP works so well, but turns out most people get tired of waving their hands around so opt for keyboard/mouse. what are you working on? would love to follow your journey
English
0
0
2
42
Joseph Demarais
Joseph Demarais@JoeDemarais·
@edwardahn9 20/ One more thing worth saying directly: any XR paradigm built around game controllers and artificial locomotion has an accessibility ceiling it can never break through, those problems can be mitigated, never solved.
English
1
0
1
30
Edward Ahn
Edward Ahn@edwardahn9·
@MuchRockness haha I agree though a few years ago I would've disagreed as someone who still believes in 3D telepresence, I'm begging Apple to make it even more seamless. shareplay is cumbersome, mandatory persona updates make calling clunky, and an apple version of hyperscape would be unreal
English
0
0
2
83
James Kelley
James Kelley@MuchRockness·
Bruh. Photorealistic avatars can't just LOOK like the user. They have to MOVE like the user. And the only way you can even HOPE to attain that, is with face-tracking, which your target device, Quest 3, doesn't have. The other issue is that nobody cares about a feature in a vacuum. It has to be DEEPLY INTEGRATED across the platform. Apple understands this with Personas.
Edward Ahn@edwardahn9

x.com/i/article/2023…

English
1
1
2
540
Edward Ahn
Edward Ahn@edwardahn9·
@dannyaroslavski well said I could not agree more. my personal take is it's really the only thing that matters now, not even price
English
0
0
1
45
Edward Ahn
Edward Ahn@edwardahn9·
@zacrane I agree. the search for it will continue for me, but just as side projects!
English
0
0
2
252
Zachary Crane
Zachary Crane@zacrane·
@edwardahn9 Great overview. Indeed, where's the killer app? I will say I think there's one out there that doesn't require full day use of the headset but will justify the purchase. Look at cars - many people buy a $40,000 vehicle and then drive it for no more than one hour a day.
English
1
0
2
416
Edward Ahn
Edward Ahn@edwardahn9·
@senderPath you and me both! i love everything about the vision pro. every time I put it on I'm in awe and I also love my facetimes. i'll be the first buyer once it's light enough to put on for a whole day
English
1
0
3
152
David Ungar
David Ungar@senderPath·
@edwardahn9 I wish I could prove you wrong, but I’m afraid you are likely right. I love the experience on my vision pro and think that mixed reality user interfaces for computing could be so much more. And I have one friend with whom I have so my weekly avatar FaceTimes. Fantastic!
English
1
0
0
186
Edward Ahn
Edward Ahn@edwardahn9·
@Da_Real_Hugo agree with you on all of these takes, esp on your point about venture-scale - the reality is venture-scale requires scale that doesn't quite exist yet, entertainment or not eg. VRChat has 40k DAU, huge in XR, but it's really quite small in the social networking space
English
0
0
2
25
Jonathan Chavez ᯅ 🇵🇦
Jonathan Chavez ᯅ 🇵🇦@Da_Real_Hugo·
@edwardahn9 That said, I'm very optimistic that some of the emerging ecosystems (AndroidXR, but SteamOS/Linux especially) that will allow for the type of experimentation that gets us closer to a paradigm shift. Personally, I think we're still in the late 70s/early 80s to use the PC analogy
English
1
0
1
33
Shawn Whiting
Shawn Whiting@ShawnCWhiting·
@edwardahn9 Great write up. We're deff still firmly in enthusiast gaming device mode - outside of a few exceptions you mentioned. It'll be fun to see how the pivot to lighter weight everyday sunglasses type devices works out.
English
1
0
1
300
Dave Smiddy
Dave Smiddy@davesmiddy·
@edwardahn9 It's a very challenging category. Growth is super expensive (lots of churn). Can fool the eyes/ears but terrible at fooling vestibular sys. Comfort is a big problem (churn!). Lots of lessons learned, I am sure. Good luck with what ever is next 🙏🏼
English
1
0
1
202
Edward Ahn
Edward Ahn@edwardahn9·
@Ryanrz yes, cleaning things up to open-source! hoping i can contribute one more thing to the community of believers I love being a part of
English
0
0
5
151
ryanrz.skr
ryanrz.skr@Ryanrz·
@edwardahn9 Appreciate you sharing your story. It’s very difficult to navigate an early market. What will you do with the avatar IP you developed? Are there parts worth open sourcing?
English
1
0
3
254
Ashwin Lalendran
Ashwin Lalendran@ashwinl·
Appreciate you sharing this. Congrats on making the bet! I wish Meta was this self-aware “What I didn’t expect was for us to still be at step one. Though over the last four years InPerson has been able to produce stunning, impressive demos of hyperrealistic avatars, the problem remains that no one actually owns a headset. We couldn’t acquire users because there were no users. What I thought were general computing devices were still gaming devices; not quite there for the masses to use” x.com/ashwinl/status…
English
1
0
1
275