abraham

designer and developer. @caltech @snap

[abraham @AbrahamDevs]

@spencermateega @nvidia @huggingface exciting !

[Fei-Fei Li @drfeifei]

I'm so excited that our @theworldlabs team has achieved a major milestone today! Introducing Atlas - a first of its kind multimodal world model trained from scratch! 🚀

Atlas is capable of generating frames with pixel-perfect camera control, reconstructing large scenes from as few as one single input image, simulating space-time by reframing videos, natively outputting 3D spaces from one or more input images, composing multiple posed images into a consistent 3d world, and more! This is the best camera conditioned world model ever, opening doors to many possible use cases from VFX to robotics. I'm so so so proud of our team!♥️

[Ivan Fioravanti @ivanfioravanti]

Sherry quantization method by Tencent, combined with large Hy4 Preview is able to deliver incredible results!
1.5TB to 214GB using 1.25 bits weights while keeping incredible accuracy!

BF16 vs Sherry:
- MCP Atlas 83.7→83.2
- SWE-Bench multi 82.9→81.3
- MRCR 81.3→81.1
- IFBench 73.5→72.5

[Spencer Mateega @spencermateega]

The Moonshot team is cracked.

[abraham @AbrahamDevs]

10/ Next I’m adding more tasks around writing-flow polish, interaction details, and multi-step product persistence.

The goal is a portfolio-grade dashboard showing metrics, diffs, screenshots, and human review side by side.

[abraham @AbrahamDevs]

I built TasteBench to evaluate whether agents can make product-quality app changes, not just code that compiles.
The interesting signal wasn’t correctness.
It was taste: copy, hierarchy, restraint, interaction feel, and design-system hygiene.
https://t.co/XMwfjKlZn4

[abraham @AbrahamDevs]

9/ TasteBench’s thesis:

The next useful coding-agent benchmarks won’t only ask “did the model solve the task?”

They’ll ask: did it preserve the product?

[abraham @AbrahamDevs]

1/ The test app is Mira, a small SwiftUI journaling app. Agents get product/design tasks, then I score both objective code signals and subjective product taste.

[abraham @AbrahamDevs]

this is wild. likely at scale it may not keep up but it goes to show how much you can do in a weekend

[Will Chen @willchen500]

Harvey is valued at $11B. Legora just raised at $5.5B. I built their entire web application in two weeks and I'm making it open-source and free for everyone to use. Say hi to Mike: https://t.co/NdtTt5MSJ2.

When I got the chance to try Harvey and Legora, I was surprised by how simple they were. A thought came to mind: I could probably build something similar in no time at all with Claude. And so I did.

Assistant, project, tabular review and workflows. You get it all without vendor lock-in.

Mike offers law firms an alternative, where they own the application layer and aren't stuck with a vendor they're renewing forever.

You can try Mike in the demo on the website, or go to the GitHub link on the site to download the code and run a local version yourself.

[abraham @AbrahamDevs]

nous research is king

[emily sihan zhang @emilyzsh]

embedded MoMA's collection of 100,000 artworks with gemini's new multimodal model so you can now explore the archive with text+img semantic search, artwork similarity, visual crops, artist collections, and more xx

built like a full browser experience - because art, like the web, is always connected 🌐

[Hamel Husain @HamelHusain]

I have very few notifications turned on but this guy's tweets is one of them, its a constant stream of the most useful tools