Not really. I am not saying CNNs were bad in what they were doing. But comparing to a frontier model, I believe frontier models have an advantage over them. Not any other model, only frontier models. I create end to end AI/ML pipelines for clients usecases, so telling with experience.
Yeah but there has been no evidence to suggest that a frontier language model is going to be better at such a domain specific niche task than a vision model trained specifically for that task. This is not the same discussion as a foundation model vs CNNs (which in my opinion would have made for a better blog post than what OP tested)
A doctor is supposed to do an anamnesis each time it might have some consequences. This is not because they are stupid, or thing you are. People simply have error rates. Just because he wants to hear everything again from the beginning, does not mean he hasn't read your file. He want's to make sure, nothing got lost or forgotten including by the patient himself. And he is actually supposed to do so, if he doesn't that's bad practice.
In particular, where cost is the x axis, a well-funded company with a good but not best model can discount their new model until it reaches the frontier. In some sense this is as much a statement about the efficiency of markets in the presence of public measurement-based comparison and public list pricing as it is about research pace.
Hi, I'm the creator. Not at all: I started this project completely by hand about a year ago, the first commit is from September 2025, you can check. Then I chose to speed up some features with automatic programming, otherwise I wouldn't have had the time
>Pioneer Craig Reynolds shares his groundbreaking work in artificial life and computer animation. Reynolds describes his lifelong fascination with simulating natural complexity computationally. By modeling flocking birds from the bottom up, based on simple rules for how individual birds move, Reynolds made the astonishing flock emerge. This agent-based approach allowed new insights into collective behavior impossible to gather from nature alone. Reynolds reflects on the significance of his iconic 1987 "Boids" model for animating birds in films like Batman Returns. But its influence extends further - to complexity science and understanding real-world systems like traffic flow and crowd dynamics. According to Reynolds, the beauty of simple models is their emergent properties. By distilling phenomena to basic rules, computer simulation uncovers new truths about the world. Join this fascinating conversation with a legend of artificial life and computer graphics.
Thanks, I appreciated your analysis. By the way, Reynolds has been credited in the README since its first version. I first heard of his boids in an introductory AI course (multi-agent systems, search algorithms, adversarial search, CSP, planning, etc.) and I was immediately fascinated by the algorithm
>OpenSteer is a C++ library for constructing steering behaviors for autonomous characters in games and animation. In addition to the library, OpenSteer provides an OpenGL-based application called OpenSteerDemo which demonstrates a variety of steering behaviors. The user can quickly prototype, visualize, annotate and debug new steering behaviors by writing a plug-in for OpenSteerDemo. [...]
>OpenSteer was initially developed by Craig Reynolds beginning in 2002 at the Research and Development group of Sony Computer Entertainment America. The OpenSteer authors wish to acknowledge the support of SCEA, SCEI and in particular these executives who had the foresight to release this code as open source for all to use: Shin'ichi Okamoto, Masa Chatani and Dominic Mallinson.
Also there's Blender's boids system, which has two main ancestors: Craig Reynolds' behavioral animation research, and Janne Karhu's rewrite of Blender's particle system. Its evolution turned the classic flocking model into an animator-controlled toolkit for flocks, herds, pursuit, and simple battles.
reply