BioComputing Co. 将活体神经元实验转化为 Wan 2.2 加速 API
BioComputing Co. 将电极上的活体人脑神经元实验应用于开放权重的视频模型 Wan 2.2，并以 API 形式提供。其方法新增参数不到 0.1%，公司称可保持 Wan 2.2 的质量并实现 5 倍速度。该实验让约 4,000 个电极上的神经元接收图像电刺激并形成自主网络，再解码其响应以改进 AI 模型，最终交付的模型不包含活体细胞。
Truly Wild stuff: a lab grew living brain cells, studied how they think, and shipped what it learned as an API you can call today.
TBC mischief 1 is that API: findings from neurons on electrodes, applied to an existing image-to-video model (Wan 2.2) .
mischief 1 applies a layer of this kind to Wan 2.2, adding less than 0.1% to its parameters, and the company claims it matches Wan 2.2’s quality at 5x the speed.
@BioComputingCo grows living human brain cells on chips with about 4,000 electrodes, where the neurons form their own networks, receive images as electrical stimulation, and their responses are decoded to improve AI models.
The path from dish to endpoint:
> Grow neurons on electrodes
> Measure how they process information
> Take an existing open-weight video model and change it based on those observations
> Ship the model, with no cells inside
来源：rohanpaul_ai · x.com