如何"偷"闭源模型的思维链
最近,一篇名为 Stealing Reasoning Traces from Proprietary LLM APIs 的文章引发了广泛讨论。顾名思义,这篇文章提出了一种从闭源 LLM API 中提取 reasoning trace(思维链)的方法。
这篇文章挺有意思的,虽然有些标题党,但给很多人增长了见识,这里就简单聊聊。
最近,一篇名为 Stealing Reasoning Traces from Proprietary LLM APIs 的文章引发了广泛讨论。顾名思义,这篇文章提出了一种从闭源 LLM API 中提取 reasoning trace(思维链)的方法。
这篇文章挺有意思的,虽然有些标题党,但给很多人增长了见识,这里就简单聊聊。
介绍英语发音,包括音标、英语元音以及特殊发音规则。本文以通用美式英语(General American, GA)为例。
参考资料:
Youtube channels are also helpful, such as [@rachelenglish](https://www.youtube.com/@rachelsenglish).
Sources:
Also, it's recommended to read my DDPM and Improved DDPM post to fully understand the context of diffusion models.
Sources:
这两年代理软件管得比较严,但 ChatGPT 对科研和学习又不可或缺。通常的解决办法是找更稳定的代理节点,也就是俗称的“机场”。不过,如果你手上有一台本身已经能访问外网的远程服务器(别管是怎么来的),也可以换一种思路:让本机通过 SSH 连接这台服务器,再把它作为本机的网络出口。这样一来,本机访问网站时,流量会先走到服务器,再由服务器访问目标网站。
Straight-through estimator, or STE, is a trick for training models that contain non-differentiable operations, notably the quantization operation commonly used in VQ-VAE.
The core idea is:
Use the non-differentiable operation in the forward pass, but replace its gradient with a simple surrogate in the backward pass.
Model Predictive Control (MPC) is a model-based planning method widely used in model-based reinforcement learning.
Sources:
Straight-through Gumbel-softmax is a trick for training models with discrete latent variables, similar to the famoud straight through estimator (STE) trick used in VQ-VAE.
The problem is simple:
We want to sample a discrete category in the forward pass, but we still want gradients to flow through it in the backward pass.
本文介绍 DJI Mic Mini 一代的使用方式,对二代及其他版本也适用。
Sources:
问题:在本地通过 SSH 登录远程服务器并进入后者的 tmux session 时,经常遇到 GitHub SSH 认证失败问题:
[email protected]: Permission denied (publickey). |