Feyn

Intelligence shaped by you

[Feyn @FeynAI]

https://t.co/BBOZS1FJa0

[Feyn @FeynAI]

Critic is in early beta. Sign up for free at https://t.co/786iYd86aE

[Feyn @FeynAI]

Today we're releasing Critic, a platform to review the code your agents write. Try it out at https://t.co/kQb5W9PRg9

Since agents started writing our code, it has become harder to understand the scope of a change. Your AI has all the context behind the code but you don't.

Critic lets the agent explain what changed and why, and answer questions from anyone reviewing its work.

[Feyn @FeynAI]

Security is a big focus for Critic. All prompts sent by critic run in a forked thread with read-only tools. That way, a Critic initiated prompt can only answer questions about the change at hand, and nothing else.

[Feyn @FeynAI]

Read more about MultiMatte https://t.co/IdgsQkoxI3 or build with it using NoBg.

MultiMatte is open source. Check it out on HuggingFace: https://t.co/6SrORT4yvy

[Feyn @FeynAI]

Introducing MultiMatte, a background removal model you can aim with words. Name an object in your image, MultiMatte keeps just that thing and cuts the rest.

Same photo, three prompts: the dog, the dog bowl, the jeans.

Try it out: https://t.co/Q15K3xjGCX

[Feyn @FeynAI]

MultiMatte is built on Meta's SAM 3. Our biggest win came from converting binary masks that classify each pixel as being inside or outside an object, to alpha mattes that assign an opacity value to every pixel. This allows MultiMatte to better understand hair, motion blur, translucency, and fuzzy boundaries.

Across all our measured benchmarks, MultiMatte shows a step improvement over SAM 3. On DIS5K, S-measure rises from 0.674 to 0.908 (a 34.6% relative gain), and on DUT-OMRON from 0.792 to 0.901 (13.7%).

[Feyn @FeynAI]

This could be you https://t.co/0enSI21D6y

[Michael @michael_chomsky]

small models are magical

250ms p50 where Cerebras would be seconds and bankrupt me (better quality too)

if you have any cool useful small models for me to try, dm me!

[Feyn @FeynAI]

The assistant that gets you, powered by Feyn

[Feyn @FeynAI]

Building FeyNoBg also exposed a tooling problem. Image matting models usually live in isolated repos with different interfaces.

So we built NoBg, a Python library for running, training models, and evaluating image mating models. Currently, it supports BiRefNet with more architectures coming. We hope you use it to build something exciting.

https://t.co/eWHc0MJcdI

[Feyn @FeynAI]

FeyNoBg and NoBg are both open source.

- Model: https://t.co/PXDqLDhQ7Q
- Try it: https://t.co/EGR4vpC3Jr
- NoBg Library: https://t.co/fO2rqOhz9y
- Technical Blog: https://t.co/XwCsRypHic

[Feyn @FeynAI]

We’re releasing FeyNoBg, our open-source model for image background removal.

Across eight benchmarks, it sets the best published S-measure on four and comes within 2% of the leader on the rest.

Try it out: https://t.co/EGR4vpC3Jr

[Feyn @FeynAI]

Building FeyNoBg also exposed a tooling problem. Image matting models usually live in isolated repos with different interfaces.

So we built NoBg, a Python library for running, training models, and evaluating image mating models. Currently, it supports BiRefNet with more architectures coming. We hope you use it to build something exciting.

https://t.co/eWHc0MJcdI

[Feyn @FeynAI]

https://t.co/ieGNPaDBMI

[Feyn @FeynAI]

To develop SQRL, we first trained SQRL-35B-A3B as the teacher, then distilled its successful inspection trajectories into smaller 4B and 9B models.

Read more about how we developed SQRL: https://t.co/KaFpVC7NqF

[Feyn @FeynAI]

https://t.co/qyJZrVqZj1

[Feyn @FeynAI]

We’re introducing SQRL, a family of small text-to-SQL models.

On the BIRD Dev benchmark, SQRL's 35B, 9B, and 4B models beat Claude Opus on SQL execution accuracy.

[Feyn @FeynAI]

SQRL is open source and available on Hugging Face. The 9B model is our recommended default.

https://t.co/PNRX4rCTq3