Feyn (@FeynAI) header
Feyn (@FeynAI) profile picture

Intelligence shaped by you

San Francisco
Joined December 2024
Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)Photo by Feyn (@FeynAI)
Can AI really do your job? We put 20 AI models in a work simulation, asking them to read their environment and do work without being asked. The latest models did 20% of planned work well enough to accept unchanged. In January, this number was 7%.
1
1
2
9
400
Models are improving fast at noticing things. That's mostly why they're getting better doing the jobs. January's models attempted only a quarter of planned work. The latest models attempt more than half.
1
1
15
This work was cheap too. The latest models cost $7 per hour of finished work. The average human labor hour costs $58
1
2
20
Critic is in early beta. Sign up for free at critic.run
2
26
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.
1
2
29
Critic is for agents too. Through the bundled MCP, your agent can pull a diff with the author’s reasoning attached, ask the authoring agent questions, and work through decisions directly. Let your agents talk to to each other
1
2
44
See which changes need your attention. Open a diff to read the change narrative written by the authoring agent. Have a question? Ask the agent that wrote it without ever leaving review
1
2
103
Today we're releasing Critic, a platform to review the code your agents write. Try it out at critic.run 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.
3
1
2
6
1,324
Read more about MultiMatte xitter.gq/status/209779722711277… or build with it using NoBg. MultiMatte is open source. Check it out on HuggingFace: hf.co/feyninc/multimatte
3
40
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%).
1
4
106
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: usefeyn.com/multimatte
1
3
1
8
929
This could be you usefeyn.com/interest/
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!
1
2
4
843
The assistant that gets you, powered by Feyn
This quoted post is unavailable.
2
4
1
16
2,377
Feyn retweeted
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. github.com/feyninc/nobg
1
1
4
237
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. github.com/feyninc/nobg
1
1
4
237
In training, a diverse data mix matters. Our first fine-tune used one dataset. It improved performance on camouflage images, but regressed elsewhere. We took this as a data problem and built a 26.1K-image mix from 10 datasets covering camouflage, crowded scenes, high-res subjects, portraits, and anime.
1
1
130
We took an interpretability-first approach for building FeyNoBg We studied the architecture of an existing model, BiRefNet. This led us to discover the importance of the third stage of its feature extractor. We expanded this stage from 18 to 24 blocks, giving it room to learn.
1
2
231