微软发布了一整条基于 LLM 的开发链：
Semantic Kernel (SK) is a lightweight SDK enabling integration of AI Large Language Models (LLMs) with conventional programming languages. The SK extensible programming model combines natural language semantic functions, traditional code native functions, and embeddings-based memory unlocking new potential and adding value to applications with AI.
https://github.com/microsoft/semantic-kernel
Semantic Kernel (SK) is a lightweight SDK enabling integration of AI Large Language Models (LLMs) with conventional programming languages. The SK extensible programming model combines natural language semantic functions, traditional code native functions, and embeddings-based memory unlocking new potential and adding value to applications with AI.
https://github.com/microsoft/semantic-kernel
GitHub
GitHub - microsoft/semantic-kernel: Integrate cutting-edge LLM technology quickly and easily into your apps
Integrate cutting-edge LLM technology quickly and easily into your apps - microsoft/semantic-kernel
DPS Build
Apple 官方的 neural engine 推理加速 SDK — 直接让 PyTorch 的推理速度提速十倍 Use ane_transformers as a reference PyTorch implementation if you are considering deploying your Transformer models on Apple devices with an A14 or newer and M1 or newer chip to achieve up to 10 times…
GitHub
GitHub - hollance/neural-engine: Everything we actually know about the Apple Neural Engine (ANE)
Everything we actually know about the Apple Neural Engine (ANE) - hollance/neural-engine
利用 ChatGPT API 来总结 Sam Altman 的访谈
https://reccap.it/recaps/sam-altman-openai-ceo-on-gpt-4-chatgpt-and-the-future-of-ai-lex-fridman-podcast--38c54630577d44a0b5423d623dccc254
https://reccap.it/recaps/sam-altman-openai-ceo-on-gpt-4-chatgpt-and-the-future-of-ai-lex-fridman-podcast--38c54630577d44a0b5423d623dccc254
Reccap
Sam Altman: OpenAI CEO on GPT-4, ChatGPT, and the Future of AI | Lex Fridman Podcast #367
Reccap enables you learning from Youtube videos at your own pace. Given a video, Reccap can extract the slides, the high-level summary and all key poinst. Reccap makes your learning and resarching 10x faster and effectiv Reccap makes your learning and resarching…
ChatGPT 救了一只狗：
In the meantime, it occurred to me that medical diagnostics seemed like the sort of thing GPT4 could potentially be really good at, so I described the situation in great detail.
I gave it the actual transcribed blood test results from multiple days, and asked for a diagnosis
When we reached the second vet, I asked if it's possible it might be IMHA.
The vet agreed that it's a possible diagnosis. They drew blood, where they noticed visible agglutination.
After numerous other tests, the diagnosis was confirmed. GPT4 was right.
https://twitter.com/peakcooper/status/1639716822680236032
In the meantime, it occurred to me that medical diagnostics seemed like the sort of thing GPT4 could potentially be really good at, so I described the situation in great detail.
I gave it the actual transcribed blood test results from multiple days, and asked for a diagnosis
When we reached the second vet, I asked if it's possible it might be IMHA.
The vet agreed that it's a possible diagnosis. They drew blood, where they noticed visible agglutination.
After numerous other tests, the diagnosis was confirmed. GPT4 was right.
https://twitter.com/peakcooper/status/1639716822680236032
Sparks of Artificial General Intelligence: Early experiments with GPT-4
https://arxiv.org/pdf/2303.12712v1.pdf
https://arxiv.org/pdf/2303.12712v1.pdf
Here we show a proof of concept using OpenAI’s chatgpt-retrieval-plugin with Meta’s LLaMA language model.
This is more than just a guide. It is a call-to-action to build an open protocol for foundation model plugins allowing us to share plugins across LLMs, and govern their interactions.
https://medium.com/m/global-identity-2?redirectUrl=https%3A%2F%2Fblog.lastmileai.dev%2Fusing-openais-retrieval-plugin-with-llama-d2e0b6732f14
This is more than just a guide. It is a call-to-action to build an open protocol for foundation model plugins allowing us to share plugins across LLMs, and govern their interactions.
https://medium.com/m/global-identity-2?redirectUrl=https%3A%2F%2Fblog.lastmileai.dev%2Fusing-openais-retrieval-plugin-with-llama-d2e0b6732f14
GitHub
GitHub - openai/chatgpt-retrieval-plugin: The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking…
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language. - openai/chatgpt-retrieval-plugin
使用 postgres 的 pgvetor 插件来存储 embedding 数据，作为 LLM 的输入。
https://supabase.com/blog/openai-embeddings-postgres-vector
https://supabase.com/blog/openai-embeddings-postgres-vector
Supabase
Storing OpenAI embeddings in Postgres with pgvector
An example of how to build an AI-powered search engine using OpenAI's embeddings and PostgreSQL.
👍1
DPS Build
围绕着 ChatGPT API 写了两周代码，记录一些想法： 1. ChatGPT API 自 gpt-turbo-3.5 发布以来，做了大大的简化。只需要在请求里写两个参数：model 和 messages，其他参数都被隐藏了。 2. 需要调整输出的话，只需要在 messages 写 prompts，通过自然语言就能控制模型的输出。大大降低了开发难度，又给输出添加了无限可能 3. 不仅 API 的交互得以大大简化，围绕着 ChatGPT API 开发的话，也可以大大简化整个 NLP 项目的开发。它…
最近又被拉着写 prompt。大前提是，隔壁组的数据出了问题，他们期望用 ChatGPT API 来批量清洗数据，他们在 ChatGPT UI 上做了测试，然后丢到我们手上。
我了解了需求之后，没看他们的 prompt，直接凭经验开始做各种尝试，最后试出了一个还不错的 prompt。于是封装成函数之后，交给后端的同事集成到流水线上。
我们跑了一小批数据，结果还不错，但是对照着隔壁组的要求，似乎不完全一致。于是后端同事直接把隔壁组的 prompt 搬进流水线里，又测试了一遍，结果和 ChatGPT UI 上的结果完全不一样。我们猜测是因为 ChatGPT UI 上还有一些后处理的逻辑。又测试了一些 prompts 之后，最后还是我提供的 prompts 效果最好。
Takeaways:
1. ChatGPT UI 和 ChatGPT API 的 prompts 不完全一致，前者有后处理逻辑，后者应该是模型直接的输出结果；
2. prompts 的确需要不断地尝试，所以 prompt engineering 可能真的是一门学问。
我了解了需求之后，没看他们的 prompt，直接凭经验开始做各种尝试，最后试出了一个还不错的 prompt。于是封装成函数之后，交给后端的同事集成到流水线上。
我们跑了一小批数据，结果还不错，但是对照着隔壁组的要求，似乎不完全一致。于是后端同事直接把隔壁组的 prompt 搬进流水线里，又测试了一遍，结果和 ChatGPT UI 上的结果完全不一样。我们猜测是因为 ChatGPT UI 上还有一些后处理的逻辑。又测试了一些 prompts 之后，最后还是我提供的 prompts 效果最好。
Takeaways:
1. ChatGPT UI 和 ChatGPT API 的 prompts 不完全一致，前者有后处理逻辑，后者应该是模型直接的输出结果；
2. prompts 的确需要不断地尝试，所以 prompt engineering 可能真的是一门学问。
👍9
DPS Build
关于 Apple neural engine 的细节 https://github.com/hollance/neural-engine
读了一遍 repo 里所有的文档，有些很有意思的点：
1. Apple Neural Engine (ANE) 是和 CPU/GPU 不一样的计算核心，专门用来处理神经网络的计算。理想的情况下，最好把所有神经网络的计算任务交给 ANE，而不是 CPU 或者 GPU；
2. 但是呢，我们无法强制指定任务给 ANE，只能告诉任务去尝试使用 ANE。大体的原因是因为，不是所有的 layer 都可以在 ANE 里计算。Core ML 会把合适的 layer 放在 ANE 里计算，把不合适的放在 CPU 或者 GPU 里计算；
3. 也就是说 Core ML 会自行判断具体的 layer 调用哪个计算核心，CPU / GPU / ANE，所以开发者只能不断尝试，将不支持的 layer 替换成支持 ANE 的 layer。
1. Apple Neural Engine (ANE) 是和 CPU/GPU 不一样的计算核心，专门用来处理神经网络的计算。理想的情况下，最好把所有神经网络的计算任务交给 ANE，而不是 CPU 或者 GPU；
2. 但是呢，我们无法强制指定任务给 ANE，只能告诉任务去尝试使用 ANE。大体的原因是因为，不是所有的 layer 都可以在 ANE 里计算。Core ML 会把合适的 layer 放在 ANE 里计算，把不合适的放在 CPU 或者 GPU 里计算；
3. 也就是说 Core ML 会自行判断具体的 layer 调用哪个计算核心，CPU / GPU / ANE，所以开发者只能不断尝试，将不支持的 layer 替换成支持 ANE 的 layer。
斯坦福开源了一个机械手臂方案，可以做非常精确的操作，比如从钱包里取出证件，用乒乓球拍颠球等等
https://twitter.com/tonyzzhao/status/1640393026341322754
https://twitter.com/tonyzzhao/status/1640393026341322754
gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue
demo 是在一台 M1 的 Mac 上跑的，输出非常快
https://github.com/nomic-ai/gpt4all
demo 是在一台 M1 的 Mac 上跑的，输出非常快
https://github.com/nomic-ai/gpt4all
GitHub
GitHub - nomic-ai/gpt4all: GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. - nomic-ai/gpt4all
👍4
用 ChatGPT API 来辅助解析抓取下来的网页，只要 写 prompts 就能清洗数据。
想法是挺好的，不过这么调取 ChatGPT 估计跟贵吧？
https://github.com/Smyja/blackmaria/tree/main/blackmaria
想法是挺好的，不过这么调取 ChatGPT 估计跟贵吧？
https://github.com/Smyja/blackmaria/tree/main/blackmaria
GitHub
blackmaria/blackmaria at main · smyja/blackmaria
Python package for webscraping in Natural language - blackmaria/blackmaria at main · smyja/blackmaria