@MaximeRivest: There is still so much to do! We know deep learning works, we just need to be a little more sharing and organized! I sp…
Summary
The author discusses the need for better sharing and organization in deep learning to make it more accessible to biologists for automating tasks like image analysis and measurement.
View Cached Full Text
Cached at: 08/17/26, 02:36 PM
There is still so much to do! We know deep learning works, we just need to be a little more sharing and organized!
I spent a whole summer internship marking and measuring flies 😅 it could be 100% automated, but the stack is still a bit to hard to be accessible to any biologists
lillyguisnet (@lillyguisnet): Heyo Biologists! We need to get together.
I’m seeing more and more published paper with teams presenting their own trained/fine-tuned models for a bunch of image/video tasks. Classification, segmentation, pose estimation, you name it! And that’s great, we’re resourceful! …but
Similar Articles
@MaximeRivest: Compound AI System for Images are way under appreciated. We need gepa, dspy, autoresearch style optimization to go from…
Maxime Rivest argues that compound AI systems for images are undervalued and suggests leveraging optimization frameworks like DSPy and GEPA to automate pipeline creation involving SAM and classifiers.
@MaximeRivest: Coding agents can only accelerate our work when we are willing to accept that we may not fully understand the overly co…
The article discusses how AI coding agents require engineers to accept that they may not fully understand the complex systems created, drawing parallels to other fields like natural resource management.
@ClementDelangue: We need 100x more transparency in AI!!!
Clement Delangue emphasizes the need for significantly greater transparency in artificial intelligence, calling for a 100x increase.
@MaximeRivest: In 2021, I trained and published a specialized character based deep neural network to classify scientification publicat…
The author discusses how their 2021 neural network for classifying scientific publications has been rendered obsolete by newer AI models like Jev and Qwen 27b.
@ClementDelangue: In biology, like in cybersecurity, we’ll learn in the coming years that most of the risk is concentrated and created by…
Clément Delangue tweeted that risks in biology and cybersecurity are concentrated in powerful labs, and open-source AI is a solution to mitigate these risks.