Let’s say you were in the market for a new laptop. What would you do? You certainly would not go on Google and search for “A good laptop under $1000”. That’d be madness. It used to be that Google could be a trusted source of information. These days, however, the top results on Google are mostly advertisements.
What Google search results look like
2024 witnessed a parade of increasingly more powerful AI model releases, culminating in OpenAI’s groundbreaking “o3”. While I’m certain these advancements really are significant, I don’t think they have translated to noticeable improvements for the average user.
What people are paying attention to, though, are the really amazing product features that are coming out of Anthropic and Google. I’ve heard a lot about people building software Claude’s Artifacts. And Google’s Deep Research product, released a few days ago, has just completely changed search.
This is a review of Open WebUI, an extensible and user-friendly self-hosted WebUI for LLMs.
I recently decided to run my own UI layer for LLMs, as I have some exciting ideas. For those who are not familiar with chatbots, their architecture basically looks like this:
While I’m pretty good at customizing the middleware, I’m not as skilled at customizing the UI layer.
I tried writing my own UI at first, but I quickly gave up when I realized it was beyond my skills as a frontend developer. The next thing I did was look into open-source solutions. There were a lot of choices, but I narrowed them down to these three:
OpenAI took the world by storm in 2023 with the relase of ChatGPT. Other companies quickly followed suit, introducing their own competitors to ChatGPT. In this update, I want to write down my thoughts on some of the biggest players in the field of generative AI.
When I use the term “generative AI,” I am referring to a computer program that can generate text, images, or other types of content. These programs can understand natural language and follow complex instructions. One notable example of a generative AI is OpenAI’s “GPT-4,” commonly known as ChatGPT. Another well-known generative AI is Midjourney, which specializes in generating images from text descriptions. In this update, I will focus on AI with text output, as that is the area I have the most experience with.
Once you know a programming language well, the process for learning a new language is not very hard. It is just time consuming. You need to read the documentation for basic syntax and flow control, get familiar with its idioms, memorize core parts of the standard libraries, and learn its tool chains. What can we do to speed up the learning process? One thing we can do is provide great examples in the documentation. Can we do better? What if you have working examples for every problem you encountered? What if you can describe your intents in a familiar language and see how it should look in a new language? As it turns out, GPT-3 is really good at this task.
Writing code with ChatGPT.
In the aftermath of ChatGPT’s debut, the Internet is abuzz with GPT’s ability to write code. I used it to write code yesterday, and this is what I thought.
I wanted to create a command line program to interact with APIs from OpenAI and AI21. The design is a single program with subcommands for each company’s APIs:
Usage: /bin/foo_to_be_named <command>
A tool to interact with various LLM models from the CLI
Flags:
-h, --help Show context-sensitive help.
--conf-file="llmcli.conf" file with api keys, created with http://localhost:8080/v1/p/tools
Commands:
openai create-completion
openai create-edit
ai21 complete
Run "/bin/foo_to_be_named <command> --help" for more information on a command.
I like to use Kong as the framework for command line parsing and I wanted to know how to use its subcommand features. Being too lazy to read the documentation, I asked ChatGPT to write me a short program using sub-commands. This is the example it came back with:
I had two weeks off at the end of 2022. Telesign closed its operations on the last week of 2022 to give employees well-deserved time off for a year of hardwork and I took another week off in addition to that. Like many technologists, I became captivated by OpenAI’s release of ChatGPT in 2022, and I spent a lot of the last two weeks exploring what OpenAI has to offer.
ChatGPT is a chatbot developed by OpenAI. It has been widely recognized for its impressive capabilities, such as imitating human writing, transforming plain English into code, and making glaringly stupid mistakes. The underlying technology of ChatGPT is a machine learning model known as GPT-3. This model is designed to predict how a human might continue a previous piece of text. For example, given what I’ve written so far, GPT-3 predicted what the rest of this blog post will look like:
My notes from Turn the Ship Around! A True Story of Turning Followers into Leaders.
I suspect, if you are in the tech industry where there is already a lot of talk about autonomy and ownership, you like already understand the theme of this book. If you believe that people need to be led or that a great personality is needed to inspire others, then you should check this out; It will offer you a useful counter perspective.
Bitch is a book from zoologist Lucy Cooke on correcting misunderstandings and cultural biases in our biological science. She explains, via animal studies, how existing notions of sex, male/female roles, and “what is natural” have been incomplete, if not incorrect.
In Bitch, Lucy goes through the behaviors of lemurs, meerkats, hyenas, moles, orcas, elephants, bonobos, termites, birds and fish to challenge conventional wisdom on nature and the roles of male and females. This alone makes for an engrossing read. I cannot help but to be delighted by learning brand new things about nature and animals. It brings me back to being a child again. What makes things better is her amusing way with words. (I am jealous.) Some choice phrases from the book:
This is a story from Neil DeGrasse Tyson’s StarTalk podcast. He talked about being on Brian Cox’s show and discussing the futures of space travel. Neil was saying that chemical rocket engines are not going to cut it and we need to look into things like wormholes and warp drives. Then Brian cuts in and explains that wormholes are fundamentally unstable and they won’t work.
Brian was absolutely correct, but that was not the point. The point was about what the audience said. Cox’s audience said to them, “That’s why the Americans discover everything! They are always so optimistic!” (Cox is a British phycisit and Neil is an American physicist).
Author: Rachel Simmons
Author: Gene Kim
I expect to learn what a badly project looks like – what are the symptoms? I expect to learn what a well-run project looks like, as well as techniques to foster a healthy project. In other words, the patterns and anti-patterns of project management.
Writing about why Emacs is hard for new users, I can’t help but think back to how important it is to name things well. This is not the first time I tried to write about this idea. I don’t think I’ve ever done a great job at it.
The thing is, naming things is really the most important way we capture ideas. Every single word we learn is an idea that has been captured and named. Let’s set aside that an idea like “cow” may mean different things to different people – that is a discussion to have elsewhere. The point I’m making is that you have now named some thing “cow” and you can use it in your thought process. Now you can in your mind imagine what a cow might when it is surrounded by predators. You might imagine what a cow might do in a crowd of people. You might imagine how that cow might behave differently based on how you and other people behave around it. You can do this because you have given a useful definition to the word “cow”. In a similar vein, useful definitions and words can help you think more clearly and hopefully, make better decisions.
True:D={x^2|x ∈ N, x >=1, x <= 4}. This reads D is the set of all x^2 SUCH THAT: 1) x is a natural number; 2) x is greater or equal to 1; 3) x is less than or equal to 4.