Ke Wang

Curious product designer exploring emerging tech, and the quiet ways it shapes us.

[Ke Wang @timescent]

So I’ve been building one:

an open, web-based XR interaction playground.

Each “lab” isolates one interaction question — selection, grab, placement, locomotion, manipulation — with live tuning and measurement built in.

[Ke Wang @timescent]

I wrote more about this in Field Notes 2/10:

Agentic Shaping, Not Just Agentic Shipping

How AI helped us work with ambiguity earlier in the product process — alongside Shape Up, not after it.

https://t.co/n1MBFnmVTS

[Ke Wang @timescent]

AI gets more interesting when the work is still ambiguous.

Not after the requirements are clear.

Before that.

When the team is shaping the problem, testing constraints, sketching options, and deciding what is worth building.

Not just agentic shipping.

Agentic shaping.

[Ke Wang @timescent]

Full LinkedIn announcement + topic preview:
https://t.co/bU1bemu0Zs

[Ke Wang @timescent]

“AI-native team” sounds clean.

Real product teams are messier:
Existing codebases
design systems
stakeholder approvals
team rituals
uneven AI confidence

I’m starting a short field notes series on building agentic workflows inside that reality.

Preview + topics on LinkedIn ↓

[Andrea Intg. @andreintg]

I was a bit hesitant about showing stuff like this just a month ago 😅

When we started showcasing real-time AI + SDF sculpting, I was afraid professionals would laugh if I showed no effort on the input models. The shape strength slider was also hidden in our first iteration, so I had no choice but to at least try and knock some more interesting shapes together.

Now that we're starting to focus on more powerful features and shape strength is finally unlocked, I'm starting to appreciate just playing with simple shapes.

Different stages of production have different needs. Sometimes you want full authoring over your creations, while other times you just want to quickly explore new ideas.

[Ali Abouelatta @abouelatta_ali]

I hated how bad agents are at design

I hated how Codex can't access Mobbin

So I created Lazyweb

- 257k+ screens (apps/web)
- 6 opinionated design research skills
- 1 MCP (Claude/Codex)

100% Free...AI native...no rate limits...no subscriptions..

Enjoy (and tell a friend) 🫡

[Ke Wang @timescent]

Coming up next:

→ Agent.md paper-to-lab scaffolding
→ graduated primitive library for cross lab experiments
→ A/B testing infrastructure
→ eye gaze + EMG primitives

Repo:
https://t.co/jjRLsmGJOK

If you work on XR interaction, try a lab and tell me what’s missing.

[Ke Wang @timescent]

Spatial computing still lacks a shared substrate for interaction experimentation.

We’re developing shared primitives — gaze, pinch, grab, ray, direct touch — but the way we build and evaluate them is still fragmented.

Every paper its own repo. Every prototype rebuilt from zero.

[Ke Wang @timescent]

For:

🔬 Researchers — evaluate new primitives quickly

🎨 Designers — feel techniques from papers, remix them

⚙️ Developers — fork primitives and push boundaries

Goal:

lower the barrier to XR interaction experimentation.

[Daniel Beauchamp @pushmatrix]

And of course the pinball table works in AR! Thanks to the amazing @react-three/xr library. Only a 100 lines of code or so to wire it up.

Load it up on your fav headset to play it in your space!

[Abhishek Bhatnagar @abhishek]

Every iPhone user deserve this 👀🔥

[Ke Wang @timescent]

We say the only difference left is consciousness and intrinsic drive.

But if something remembers, reflects, forms stable preferences, and feels real to us —

Where do you think that line actually sits?

[Ke Wang @timescent]

We don’t need AGI to recreate a person.

We just need enough coherence to trigger attachment.

[Ke Wang @timescent]

The “Be Right Back” scenario from Black Mirror once felt speculative.

Today, the primitives already exist.

Not consciousness.
Not true agency.

But long-term adaptive continuity.