Revision as of 09:28, 27 April 2024

人類如何勝過AI

人類如何勝過AI？

Applications

人何時走完全未知？美研發AI預測臨終準確度達90％
美國FDA首次批准AI醫療儀器上市，能自動即時偵測糖尿病視網膜病變
在家養老-科技幫大忙
病理研究有新幫手，Google以AR顯微鏡結合深度學習即時發現癌細胞
This New App Is Like Shazam for Your Nature Photos. Seek App.
Draw This camera prints crappy drawings of the things you photograph (DIY) with Google's quickdraw.
What Are Machine Learning Algorithms? Here’s How They Work
How to Read Articles That Use Machine Learning Users’ Guides to the Medical Literature
Google的人工智慧開源神器三歲了，它被用在很多你想不到的地方 Nov 2018
What is Natural Language Processing and How Does It Work? NLP works via preprocessing the text and then running it through the machine learning-trained algorithm.
Why Machine Learning Cannot Ignore Maximum Likelihood Estimation van der Laan & Rose 2021

Learning prompts

How to Learn Python FAST with ChatGPT?
- Can you create a roadmap to learn python for data analysis
- Can you create a roadmap to learn python for data analysis in 3 months with weekly plan and resources for learning
- Can you create a roadmap to learn python for data analysis in 3 months with weekly plan, including resources and links for each week and youtube video links
- Explain while loop in python to a child

How to learn to code FAST using ChatGPT
- Give me a study plan to learn python for data science
- Give me a study plan to learn python for data science with resources and a timeline
- Sublime is used
- (After ask a question and get an answer). Let's take this step by step.

10 Most Interesting Prompt Types: to Unlock AI's Creativity for Your Work or Business

Ask generative AI to be that colleague. Ask 'As a physicist, describe how cancer cells interact with their environment', or 'As a chemist..', 'As a developmental biologist..', 'As an economist..' 'As an electrician.' ...

The Top 5 Online Courses for Mastering AI Prompt Engineering

How I Won Singapore’s GPT-4 Prompt Engineering Competition

ChatGPT

https://chat.openai.com, https://openai.com/blog/chatgpt-plus/

https://openai.com/blog/chatgpt/
Sign Up to OpenAI without Your Phone Number | OpenAI SMS Verification,
https://beta.openai.com/overview, examples
Tip: use SHIFT + ENTER to add a line break for entering some code.
This AI chatbot is dominating social media with its frighteningly good essays 2022/12/5
how it actually works?
ChatGPT is incredibly limited, but good enough at some things to create a misleading impression of greatness
Plagiarism is an outdated concept for AI
The End of High-School English
chatGPT google extension -A browser extension to display ChatGPT response alongside search engine results
GPT-1 to GPT-4: Each of OpenAI's GPT Models Explained and Compared
Tokens
- What Is the ChatGPT Token Limit and Can You Exceed It?
- https://openai.com/api/pricing/. 0.04 - 2¢ per 1k tokens/words (language models). You can think of tokens as pieces of words, where 1,000 tokens is about 750 words. How much does the OpenAI’s cost per session? About $0.05 to $0.1, if you send 25 to 50 requests. $18.00 free trial. Cost depends on how many words in the input and output at $0.000002 per word.

9 Communities for Beginners to Learn About AI Tools

Down

Plugins

How to Enable ChatGPT’s Web Browsing and Plugins

Use

cheat sheet
The 14 Best ChatGPT Prompts on GitHub
How to Use ChatGPT for Writing Difficult Emails at Work
Can ChatGPT Be Used as a Proofreader?
The 7 Best Tools That Use AI to Make Presentations for You
- https://mindshow.fun/ 快速演示你的想法 Auto-generated Slides
Learn a language
- How ChatGPT Plus Can Help You Learn a Language
- How to Use ChatGPT's Conversational Mode to Practice a Language

Some examples:
- Andrew Ng
- Bioinformatics
- ChatGPT can Create Datasets, Program in R… and when it makes an Error it can Fix that too!
- It can also update code to more modern syntax as long as the syntax predates April 2021
- http://rtutor.ai/ which is built based on R's openai package.
  - Bioinformatics analysis using Chatlize and ChatGPT by Pr. Steven Ge | Tunis R User Group |Workshop 3
- 15 Creative Ways to Use ChatGPT by OpenAI
- Setting up macOS as an R data science rig in 2023
- Describe 20 possible generative AI use cases in detail across society that could create early impact.

API, Extension tools

call from R

Call ChatGPT (or really any other API) from R
openai-This R package provides an SDK to the Open AI API
openai package from CRAN & github
askgpt package
Shiny on Hugging Face

call from Python

Jupyter-ai

A generative AI extension for JupyterLab

Bing chat

It's been 18 days but Bing chat says R 4.3.0 is not yet released. It says the latest version of R is 4.1.3. The default conversion style is balanced (blue). After I changed it to more precise (green), the results are right.

Brave AI chatbot: Leo

Everything You Need to Know About Leo: Brave Browser’s AI Chatbot

GPT-4

Alternatives

The 3 Best Alternatives to ChatGPT 1/6/2023
7 ChatGPT AI Alternatives (Free and Paid) 3/1/2023

PDF

chatPDF. ChatPDF allows you to use it for free with 3 PDFs every day, each up to 120 pages. It seems I can use chatPDF as usual chatGPT after I upload/paste URL of a pdf file without signing in my account.
pdfGPT
6 ChatGPT Apps to Analyze and Chat With Your Documents and PDFs
7 AI Tools That Answer Questions From Your PDFs

Word

How to Automate Your Document Creation With ChatGPT in Microsoft Word

Research

https://elicit.org/. Trained on scientific papers, and not only biomedical ones (providing real references!)
- How to use Elicit for topics that have lots of research
The 6 Best AI Tools for Researchers and Teachers
- Research Rabbit
- Gradescope
- Education Copilot
- ReadCube Papers
- Consensus
- Elicit
Fake citations?, WebChatGPT: ChatGPT with internet access.
- To get references to journal articles, add "site:scholar.google.com" before your question.
- You can do the same exercise with another scholarly database like PubMed. site:pubmed.ncbi.nlm.nih.gov What are the major causes of lung cancer?

Content writer

7 Responsible Ways to Use AI as a Content Writer or Editor
How to Use ChatGPT to Transform Writing Into Another Format
- Turning A Blog Post Into a YouTube Script
- Changing a Technical Document Into a Popular Article
- Turning a Short Story Into a Movie Script

Detect AI text

Youtube summary

Chrome extension YouTube Summary with ChatGPT from 8 AI-Powered Chrome Extensions to Summarize YouTube Videos

AutoGPT

How to Download and Install Auto-GPT Step-by-Step

Other chats

You.com

You.com’s AI-infused Google rival provides a tantalizing glimpse of the future

Google Bard

Claude

https://claude.ai/login, https://claude.ai/chat/. Like ChatGPT, there is no internet access.
Claude vs. ChatGPT: Which LLM Is Best for Everyday Tasks?

perplexity.ai

https://www.perplexity.ai/

Meta's LLaMA

Introducing Meta Llama 3: The most capable openly available LLM to date 2024/4/18

Open source chats

HuggingChat
- GPT4All now supports 100+ more models! Sideloading any ggML model
- HuggingChat vs. Bing Chat: Which Is the Better ChatGPT Alternative?
Run Your Own AI Chat GPT-3 On Your Computer llama
1 Command To Bring Home Your Very Own Robot Overlord - Text Generation Webui
- oobabooga
How to Run a Large Language Model on Linux (and Why You Should)
- dalai

Run locally

Jan, https://github.com/janhq/jan
- ChatGPT 最佳免费替代软件！支持本地离线运行，100%免费开源，兼容多种主流AI大模型！.
- Llama 3 正式发布！性能强悍，支持AI文生图，完全免费开源！附本地安装教程！

LM Studio.
- Run local LLMs with ease on Mac and Windows thanks to LM Studio
- Llama3 一键本地部署！无需GPU ！100% 保证成功，轻松体验 Meta 最新的 8B、70B AI大模型！

Ollama

GPT4ALL
Opera Is the First Browser to Support Local AI LLMs

BERT

AI, ML and DL

AI, ML and DL: What’s the Difference?

Coding

The Top LLMs For Code Generation: 2024 Edition

Images

Drawing

Describe images

Videos

Music

Does Google's MusicLM Live Up to the Hype?

Text to/from speech

文字轉語音、語音轉文字！這幾種方法你最好要知道

Bioinformatics

AI and statistics

Artificial Intelligence and Statistics: Just the Old Wine in New Wineskins? Faes 2022

What are the most important statistical ideas of the past 50 years

Four Deep Learning Papers to Read in June 2021

Neural network

Types of artificial neural networks

https://en.wikipedia.org/wiki/Types_of_artificial_neural_networks

neuralnet package

nnet package

sauron package

Explaining predictions of Convolutional Neural Networks with 'sauron' package

OneR package

So, what is AI really?

h2o package

https://cran.r-project.org/web/packages/h2o/index.html

shinyML package

shinyML - Compare Supervised Machine Learning Models Using Shiny App

LSBoost

Explainable 'AI' using Gradient Boosted randomized networks Pt2 (the Lasso)

LightGBM/Light Gradient Boosting Machine

Survival data

Simulated neural network

Simulated Neural Network with Bootstrapping Time Series Data

Languages

GitHub: The top 10 programming languages for machine learning

Keras (high level library)

Keras is a model-level library, providing high-level building blocks for developing deep-learning models. It doesn’t handle low-level operations such as tensor manipulation and differentiation. Instead, it relies on a specialized, well-optimized tensor library to do so, serving as the backend engine of Keras.

Currently, the three existing backend implementations are the TensorFlow backend, the Theano backend, and the Microsoft Cognitive Toolkit (CNTK) backend.

On Ubuntu, we can install required packages by

$ sudo apt-get install build-essential cmake git unzip \
                  pkg-config libopenblas-dev liblapack-dev
$ sudo apt-get install python-numpy python-scipy python- matplotlib python-yaml
$ sudo apt-get install libhdf5-serial-dev python-h5py
$ sudo apt-get install graphviz
$ sudo pip install pydot-ng
$ sudo apt-get install python-opencv

$ sudo pip install tensorflow  # CPU only
$ sudo pip install tensorflow-gpu # GPU support

$ sudo pip install theano

$ sudo pip install keras
$ python -c "import keras; print keras.__version__"
$ sudo pip install --upgrade keras  $ Upgrade Keras

To configure the backend of Keras, see Introduction to Python Deep Learning with Keras.

TensorFlow (backend library)

Basic

https://www.tensorflow.org/
- https://www.tensorflow.org/install/docker
https://tensorflow.rstudio.com/
- R interface to Keras. I followed the instruction for the installation but got an error of illegal operand. The solution is to use an older version of tensorflow; see here. library(keras); install_keras(tensorflow = "1.5") (Ubuntu 16.04, Phenom(tm) II X6 1055T)
- https://rviews.rstudio.com/2018/04/03/r-and-tensorflow-presentations/, Slides
- https://hub.docker.com/r/andrie/tensorflowr/, https://hub.docker.com/r/rocker/ml/dockerfile (outdated)
Deep Learning on Biowulf
Raspberry Pi
- How to Install Tensorflow on Raspberry Pi
Books
- Deep Learning with R by François Chollet with J. J. Allaire, 2018. ISBN-10: 161729554X (available on safaribooksonline)
- Deep Learning with Python by François Chollet, 2017 (available on safaribooksonline)
- Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville
Enterprise Web Services with Neural Networks Using R and TensorFlow A docker image was created based on R 3.5.0 using R libraries from MRAN’s July 2nd, 2018 snapshot, as well as Miniconda 3 version 4.4.10 for python.
Deep Learning Glossary
- http://www.wildml.com/deep-learning-glossary/
- What is an epoch (related to batch) in deep learning?, Epoch vs Iteration when training neural networks. Example: if you have 1000 training examples, and your batch size is 500, then it will take 2 iterations to complete 1 epoch. Since "batch" depends on the partition of the entire samples, we need different partitions (epoches) in order to get an unbiased result.
Best Books to learn Tensorflow

Some terms

Machine Learning Glossary from developers.google.com

Tensor

Tensors for Neural Networks, Clearly Explained!!!

Dense layer and dropout layer

In Keras, what is a "dense" and a "dropout" layer?

Fully-connected layer (= dense layer). You can choose "relu" or "sigmoid" or "softmax" activation function.

Activation function

Artificial neural network -> Neural networks as functions [math]\displaystyle{ \textstyle f (x) = K \left(\sum_i w_i g_i(x)\right) }[/math] where K (commonly referred to as the activation function) is some predefined function, such as the hyperbolic tangent or sigmoid function or softmax function or rectifier function.
Rectifier/ReLU f(x) = max(0, x).
Sigmoid. Binary problem. Logistic function and hyperbolic tangent tanh(x) are two examples of sigmoid functions.
Softmax. Multiclass classification.

Backpropagation

https://en.wikipedia.org/wiki/Backpropagation

Convolutional network

https://en.wikipedia.org/wiki/Convolutional_neural_network

Deep Learning with Python

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

sudo apt install python3-pip python3-dev

sudo apt install build-essential cmake git unzip \
   pkg-config libopenblas-dev liblapack-dev
sudo apt-get install python3-numpy python3-scipy python3-matplotlib \
   python3-yaml
sudo apt install libhdf5-serial-dev python3-h5py
sudo apt install graphviz
sudo pip3 install pydot-ng

# sudo apt-get install python-opencv
# https://stackoverflow.com/questions/37188623/ubuntu-how-to-install-opencv-for-python3
# https://askubuntu.com/questions/783956/how-to-install-opencv-3-1-for-python-3-5-on-ubuntu-16-04-lts

sudo pip3 install keras

Colorize black-and-white photos

Keras using R

R Markdown Notebooks for "Deep Learning with R"
R interface to Keras
Deep Neural Network in R
Python vs R
Derivative of a tensor operation: the gradient
- Define loss_value = f(W) = dot(W, x)
- W1 = W0 - step * gradient(f)(W0)
Stochastic gradient descent
Tensor operations:
- relu(x) = max(0, x)
- Each neural layer from our first network example transforms its input data:output = relu(dot(W, input) + b) where W and b are the weights or trainable parameters of the layer.

Training process:

Draw a batch of X and Y
Run the network on x (a step called the forward pass) to obtain predictions y_pred.
- How many layers to use.
- How many “hidden units” to chose for each layer.
Compute the loss of the network on the batch
- loss
- optimizer: determines how learning proceeds (how the network will be updated based on the loss function). It implements a specific variant of stochastic gradient descent (SGD).
- metrics
Update all weights of the network in a way that slightly reduces the loss on this batch.
- batch_size
- epochs (=iteration over all samples in a batch_size of samples)

Keras (in order to use Keras, you need to install TensorFlow or CNTK or Theano):

Define your training data: input tensors and target tensors.

Define a network of layers (or model). Two ways to define a model:

using the keras_model_sequential() function (only for linear stacks of layers, which is the most common network architecture by far) or

model <- keras_model_sequential() %>%
  layer_dense(units = 32, input_shape = c(784)) %>%
  layer_dense(units = 10, activation = "softmax")

the functional API (for directed acyclic graphs of layers, which let you build completely arbitrary architectures)

input_tensor <- layer_input(shape = c(784))

output_tensor <- input_tensor %>%
  layer_dense(units = 32, activation = "relu") %>%
  layer_dense(units = 10, activation = "softmax")

model <- keras_model(inputs = input_tensor, outputs = output_tensor)

Compile the learning process by choosing a loss function, an optimizer, and some metrics to monitor.

model %>% compile(
  optimizer = optimizer_rmsprop(lr = 0.0001),
  loss = "mse",
  metrics = c("accuracy")
)

Iterate on your training data by calling the fit() method of your model.

model %>% fit(input_tensor, target_tensor, batch_size = 128, epochs = 10)

Custom loss function

Custom Loss functions for Deep Learning: Predicting Home Values with Keras for R

Metrics

https://machinelearningmastery.com/custom-metrics-deep-learning-keras-python/

Docker RStudio IDE

Assume we are using rocker/rstudio IDE, we need to install some packages first in the OS.

$ docker run -d -p 8787:8787 -e USER=XXX -e PASSWORD=XXX --name rstudio rocker/rstudio

$ docker exec -it rstudio bash
# apt update
# apt install python-pip python-dev
# pip install virtualenv

And then in R,

install.packages("keras")
library(keras)
install_keras(tensorflow = "1.5")

Use your own Dockerfile

Data Science for Startups: Containers Building reproducible setups for machine learning

Some examples

See Tensorflow for R from RStudio for several examples.

Binary data (Chapter 3.4)

The final layer will use a sigmoid activation so as to output a probability (a score between 0 and 1, indicating how likely the sample is to have the target “1”.
A relu (rectified linear unit) is a function meant to zero-out negative values, while a sigmoid “squashes” arbitrary values into the [0, 1] interval, thus outputting something that can be interpreted as a probability.

library(keras)
imdb <- dataset_imdb(num_words = 10000)
c(c(train_data, train_labels), c(test_data, test_labels)) %<-% imdb

# Preparing the data
vectorize_sequences <- function(sequences, dimension = 10000) {...}
x_train <- vectorize_sequences(train_data)
x_test <- vectorize_sequences(test_data)
y_train <- as.numeric(train_labels)
y_test <- as.numeric(test_labels)

# Build the network
## Two intermediate layers with 16 hidden units each
## The final layer will output the scalar prediction
model <- keras_model_sequential() %>% 
  layer_dense(units = 16, activation = "relu", input_shape = c(10000)) %>% 
  layer_dense(units = 16, activation = "relu") %>% 
  layer_dense(units = 1, activation = "sigmoid")
model %>% compile(
  optimizer = "rmsprop",
  loss = "binary_crossentropy",
  metrics = c("accuracy")
)
model %>% fit(x_train, y_train, epochs = 4, batch_size = 512)
## Error in py_call_impl(callable, dots$args, dots$keywords) : MemoryError: 
## 10.3GB memory is necessary on my 16GB machine

# Validation
results <- model %>% evaluate(x_test, y_test)

# Prediction on new data
model %>% predict(x_test[1:10,])

Multi class data (Chapter 3.5)

Goal: build a network to classify Reuters newswires into 46 different mutually-exclusive topics.
You end the network with a dense layer of size 46. This means for each input sample, the network will output a 46-dimensional vector. Each entry in this vector (each dimension) will encode a different output class.
The last layer uses a softmax activation. You saw this pattern in the MNIST example. It means the network will output a probability distribution over the 46 different output classes: that is, for every input sample, the network will produce a 46-dimensional output vector, where outputi is the probability that the sample belongs to class i. The 46 scores will sum to 1.

library(keras)
reuters <- dataset_reuters(num_words = 10000)
c(c(train_data, train_labels), c(test_data, test_labels)) %<-% reuters

model <- keras_model_sequential() %>% 
  layer_dense(units = 64, activation = "relu", input_shape = c(10000)) %>% 
  layer_dense(units = 64, activation = "relu") %>% 
  layer_dense(units = 46, activation = "softmax")
model %>% compile(
  optimizer = "rmsprop",
  loss = "categorical_crossentropy",
  metrics = c("accuracy")
)
history <- model %>% fit(
  partial_x_train,
  partial_y_train,
  epochs = 9,
  batch_size = 512,
  validation_data = list(x_val, y_val)
)
results <- model %>% evaluate(x_test, one_hot_test_labels)
# Prediction on new data
predictions <- model %>% predict(x_test)

MNIST dataset.

Regression data (Chapter 3.6)

Because so few samples are available, we will be using a very small network with two hidden layers. In general, the less training data you have, the worse overfitting will be, and using a small network is one way to mitigate overfitting.
Our network ends with a single unit, and no activation (i.e. it will be linear layer). This is a typical setup for scalar regression (i.e. regression where we are trying to predict a single continuous value). Applying an activation function would constrain the range that the output can take. Here, because the last layer is purely linear, the network is free to learn to predict values in any range.
We are also monitoring a new metric during training: mae. This stands for Mean Absolute Error.

library(keras)
dataset <- dataset_boston_housing()
c(c(train_data, train_targets), c(test_data, test_targets)) %<-% dataset

build_model <- function() {
  model <- keras_model_sequential() %>% 
    layer_dense(units = 64, activation = "relu", 
                input_shape = dim(train_data)[[2]]) %>% 
    layer_dense(units = 64, activation = "relu") %>% 
    layer_dense(units = 1) 
    
  model %>% compile(
    optimizer = "rmsprop", 
    loss = "mse", 
    metrics = c("mae")
  )
}
# K-fold CV
k <- 4
indices <- sample(1:nrow(train_data))
folds <- cut(1:length(indices), breaks = k, labels = FALSE) 
num_epochs <- 100
all_scores <- c()
for (i in 1:k) {
  cat("processing fold #", i, "\n")
  # Prepare the validation data: data from partition # k
  val_indices <- which(folds == i, arr.ind = TRUE) 
  val_data <- train_data[val_indices,]
  val_targets <- train_targets[val_indices]
  
  # Prepare the training data: data from all other partitions
  partial_train_data <- train_data[-val_indices,]
  partial_train_targets <- train_targets[-val_indices]
  
  # Build the Keras model (already compiled)
  model <- build_model()
  
  # Train the model (in silent mode, verbose=0)
  model %>% fit(partial_train_data, partial_train_targets,
                epochs = num_epochs, batch_size = 1, verbose = 0)
                
  # Evaluate the model on the validation data
  results <- model %>% evaluate(val_data, val_targets, verbose = 0)
  all_scores <- c(all_scores, results$mean_absolute_error)
}

PyTorch

An R Shiny app to recognize flower species

Google Cloud Platform

Choosing between TensorFlow/Keras, BigQuery ML, and AutoML Natural Language for text classification Comparing text classification done three ways on Google Cloud Platform

Amazon

Amazon's Machine Learning University is making its online courses available to the public

Workshops

Notebooks from the Practical AI Workshop 2019

OpenML.org

R interface to OpenML.org

Biology

Predicting Splicing from Primary Sequence with Deep Learning Jaganathan et al 2018
Intelligent diagnosis with Chinese electronic medical records based on convolutional neural networks Li et al BMC Bioinformatics 2019
DL 101: Basic introduction to deep learning with its application in biomedical related fields 2022

@@ Line 16: / Line 16: @@
 = Learning prompts =
+* [https://www.makeuseof.com/how-to-reduce-ai-hallucination/ How to Reduce AI Hallucination With These 6 Prompting Techniques]
 * [https://www.makeuseof.com/prompting-techniques-to-improve-chatgpt-responses/ 7 Prompting Techniques to Improve Your ChatGPT Responses]
@@ Line 35: / Line 36: @@
 * [https://www.makeuseof.com/online-courses-mastering-ai-prompt-engineering/ The Top 5 Online Courses for Mastering AI Prompt Engineering]
+* [https://readmedium.com/how-i-won-singapores-gpt-4-prompt-engineering-competition-34c195a93d41 How I Won Singapore’s GPT-4 Prompt Engineering Competition]
 = ChatGPT =
@@ Line 71: / Line 74: @@
 * [https://www.makeuseof.com/can-chatgpt-be-used-as-proofreader/ Can ChatGPT Be Used as a Proofreader?]
 * [https://www.makeuseof.com/tools-use-ai-to-make-presentation/ The 7 Best Tools That Use AI to Make Presentations for You]
-* [https://www.makeuseof.com/how-chatgpt-plus-can-help-you-learn-a-language/ How ChatGPT Plus Can Help You Learn a Language]
+** https://mindshow.fun/ 快速演示你的想法 Auto-generated Slides
+* Learn a language
+** [https://www.makeuseof.com/how-chatgpt-plus-can-help-you-learn-a-language/ How ChatGPT Plus Can Help You Learn a Language]
+** [https://www.howtogeek.com/chatgpt-conversational-mode-to-practice-a-language/ How to Use ChatGPT's Conversational Mode to Practice a Language]
 * Some examples:
@@ Line 79: / Line 85: @@
 ** [https://twitter.com/dr_keithmcnulty/status/1599716570569138177 It can also update code to more modern syntax as long as the syntax predates April 2021]
 ** http://rtutor.ai/ which is built based on R's [https://cran.rstudio.com/web/packages/openai/index.html openai] package.
+*** [https://www.youtube.com/watch?v=7GfyThwIF04 Bioinformatics analysis using Chatlize and ChatGPT by Pr. Steven Ge] | Tunis R User Group |Workshop 3
 ** [https://www.makeuseof.com/creative-ways-to-use-chatgpt-openai/ 15 Creative Ways to Use ChatGPT by OpenAI]
 ** [https://ivelasq.rbind.io/blog/macos-rig/index.html Setting up macOS as an R data science rig in 2023]
@@ Line 106: / Line 113: @@
 == Bing chat ==
 It's been 18 days but Bing chat says R 4.3.0 is not yet released. It says the latest version of R is 4.1.3. The default conversion style is balanced (blue). After I changed it to more precise (green), the results are right.
+== Brave AI chatbot: Leo ==
+[https://www.makeuseof.com/everything-leo-brave-ai/ Everything You Need to Know About Leo: Brave Browser’s AI Chatbot]
 == GPT-4 ==
@@ Line 126: / Line 136: @@
 * [https://www.makeuseof.com/chatgpt-apps-to-analyze-chat-with-documents-pdfs/ 6 ChatGPT Apps to Analyze and Chat With Your Documents and PDFs]
 * [https://www.makeuseof.com/ai-tools-answer-pdf/ 7 AI Tools That Answer Questions From Your PDFs]
+== Word ==
+[https://www.makeuseof.com/automate-document-creation-with-chatgpt-in-word/ How to Automate Your Document Creation With ChatGPT in Microsoft Word]
 == Research ==
@@ Line 163: / Line 176: @@
 == Google Bard ==
-[https://blog.google/technology/ai/code-with-bard/ Bard now helps you code] 4/21/2023
+* [https://blog.google/technology/ai/code-with-bard/ Bard now helps you code] 4/21/2023
+* [https://lifehacker.com/set-up-google-bard-extensions-1850853309 You Can Now Connect Bard to Gmail, Google Docs, YouTube, and More]
 == Claude ==
-* https://claude.ai/login, https://claude.ai/chat/
+* https://claude.ai/login, https://claude.ai/chat/. Like ChatGPT, there is no internet access.
 * [https://www.makeuseof.com/claude-vs-chatgpt-which-llm-is-best/ Claude vs. ChatGPT: Which LLM Is Best for Everyday Tasks?]
@@ Line 173: / Line 187: @@
 == Meta's LLaMA ==
-[https://www.makeuseof.com/raspberry-pi-large-language-model/ How to Run a Large Language Model on Your Raspberry Pi]
+* [https://ai.meta.com/blog/meta-llama-3/ Introducing Meta Llama 3: The most capable openly available LLM to date] 2024/4/18
 == Open source chats ==
@@ Line 184: / Line 198: @@
 * [https://www.makeuseof.com/run-a-large-language-model-on-linux/ How to Run a Large Language Model on Linux (and Why You Should) ]
 ** [https://github.com/cocktailpeanut/dalai dalai]
+= Run locally =
+* [https://jan.ai/ Jan], https://github.com/janhq/jan
+** [https://www.youtube.com/watch?v=gf8Phs2YXWU ChatGPT 最佳免费替代软件！支持本地离线运行，100%免费开源，兼容多种主流AI大模型！].
+** [https://www.youtube.com/watch?v=TCHnDqFdkLw Llama 3 正式发布！性能强悍，支持AI文生图，完全免费开源！附本地安装教程！]
+* [https://lmstudio.ai/ LM Studio].
+** [https://www.xda-developers.com/run-local-llms-mac-windows-lm-studio/ Run local LLMs with ease on Mac and Windows thanks to LM Studio]
+** [https://www.youtube.com/watch?v=NP0s7T9Mou8 Llama3 一键本地部署 ！无需GPU ！100% 保证成功，轻松体验 Meta 最新的 8B、70B AI大模型！]
+* Ollama
+** [https://readmedium.com/step-by-step-guide-to-running-latest-llm-model-meta-llama-3-on-apple-silicon-macs-m1-m2-or-m3-b9424ada6840 Step-by-Step Guide to Running Latest LLM Model Meta Llama 3 on Apple Silicon Macs (M1, M2 or M3)]
+** [https://fleetstack.io/blog/running-open-llm-models-on-raspberry-pi-5-with-ollama Running Open LLM Models on Raspberry Pi 5 with Ollama]
+** [https://itsfoss.com/raspberry-pi-ollama-ai-setup/ Run LLMs Locally on Raspberry Pi Using Ollama AI]
+* GPT4ALL
+* [https://lifehacker.com/tech/opera-is-the-first-browser-to-support-local-ai-llms Opera Is the First Browser to Support Local AI LLMs]
 = BERT =
@@ Line 192: / Line 223: @@
 [https://www.opensourceforu.com/2022/08/ai-ml-and-dl-whats-the-difference/ AI, ML and DL: What’s the Difference?]
-= Drawing =
+= Coding =
+[https://www.scribbledata.io/blog/the-top-llms-for-code-generation-2024-edition/ The Top LLMs For Code Generation: 2024 Edition]
+= Images =
+== Drawing ==
 * [https://www.reviewgeek.com/151292/this-new-ai-tool-can-animate-your-childrens-drawings/ This New AI Tool Can Animate Your Children’s Drawings]. [https://sketch.metademolab.com/ Animated Drawing] by Meta.
 * [https://www.makeuseof.com/react-dall-e-image-generator-application-build-api/ How to Build an Image Generator in React Using the DALL-E API ]
 * [https://www.makeuseof.com/how-to-use-bing-image-creator-ai-art/ How to Use Bing Image Creator to Make AI Art]
 * [https://youtu.be/xMrilkJ21yo How To Install Stable Diffusion With Prompting Cheat Sheets] 5/21/2023
+* [https://www.makeuseof.com/best-open-source-ai-image-generators/ The 5 Best Open-Source AI Image Generators] 2024/4/23
+== Describe images ==
+* [https://www.makeuseof.com/use-chatgpt-vision/ 8 Ways to Use ChatGPT Vision]
+* [https://www.makeuseof.com/google-bard-use-image-prompts/ How to Use Image Prompts on Google Bard]
 = Videos =
 * [https://youtu.be/OpYYFGJPr0A 超逼真的AI数字人，一键免费生成教程！还能克隆你自己，用这2个网站即可轻松搞定！！] 5/21/2023 零度解说
+* [https://www.youtube.com/watch?v=5KC4wFTLq3E 零基礎入門 全流程AI做兒童動畫頻道，月賺1w美元｜解決人物一致+嘴形問題｜Creating animation channel with AI]
 = Music =
@@ Line 210: / Line 251: @@
 * [https://academic.oup.com/bib/article/23/6/bbac409/6713511 BioGPT: generative pre-trained transformer for biomedical text generation and mining]
 * [https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9950855/ Applications of transformer-based language models in bioinformatics: a survey] 2023
+* [https://journals.plos.org/ploscompbiol/article?id=10.1371%2Fjournal.pcbi.1011319 Ten quick tips for harnessing the power of ChatGPT in computational biology] 2023
+* [https://huggingface.co/BioMistral BioMistral],
+** [https://arxiv.org/html/2402.10373v1 manuscript]
+** [https://anakin.ai/blog/biomistral-7b/ BioMistral-7B: Mistral 7B Based LLM for Medical Domains]
+** [https://www.explainx.ai/post/biomistral-a-breakthrough-in-medical-language-models Revolutionizing Healthcare with BioMistral: A Breakthrough in Medical Language Models]
+** [https://mistral-7b.com/try-installing-biomistral-on-your-windows-system-for-the-best-medical-llm-experience-this-local-installation-is-user-friendly-and-ensures-optimal-performance/ Try installing BioMistral on your Windows system for the best medical LLM experience. This local installation is user-friendly and ensures optimal performance].
 = AI and statistics =

AI: Difference between revisions