The @browsercompany 's Arc browser has some amazing UX features. These are some of my favorites (thread):

1. Hybrid Bookmark + Tabs ("Close and Keep Pinned")

This is a brilliant feature for tab/bookmark junkies.

You can pin bookmarks on the sidebar. When you click them, they behave like tabs. When you're done, you can select "Close and keep pinned", it returns to the original pinned page.

This suits my workflow so well, because I have a few aggregator pages bookmarked, and I like to browse for a bit and reset each to their home views when I'm done. I have tons of bookmarks and tabs, and blurring the lines between them is a great idea.
@browsercompany Peek Links

I like the way it handles external links. It shows them as a popup taking up most of the screen. You can click outside the popup to return to go back, or you can hit the expand button to open it in a new tab.

Eliminates lots of tab closing / back button usage

Really excited to announce a big update for the @logseq @openai #gpt3 plugin!

A UI popup that lets you use "prompt templates" or write freeform text as the prompt.

You can ask the AI to perform any task on the current block, use a built-in command, or define your own templates You can write any command in the popup, and it will run that command using text in the current block.

For example, to create flash cards for studying, you could write "create flash cards based on the following text:"

Books I read in 2022.

I wrote a short summary, my thoughts, and some excerpts I thought represented the book so you can see if it’s something you’d be interested in.

briansunter.com/pages/books-re… Some favorites:

Hard-Boiled Wonderland and the End of the World by Haruki Murakami

A human data processor trained to encrypt data with his mind to protect it from criminal groups.

Two intertwined stories between dystopian Tokyo and a strange isolated town

What is "Zero-Shot", "One-Shot", "Few-Shot", and "Fine-Tuning" in the context of @openai #gpt3?

From the #gpt3 paper
arxiv.org/pdf/2005.14165…

These terms refer to how many examples a language model needs to perform a task "Fine-Tuning" is the most common and traditional approach.

100s to 100k+ labeled examples are used. It has strong performance on many benchmarks but needs a new large dataset for every task.

It's better for specific use cases than general tasks.

Nine Principles from The Book of Earth, The Book of Five Rings by Miyamoto Musashi (1645)

Intended to be "worldly" advice for students to develop an understanding of strategy before studying his tactics and philosophy. "Do not think dishonestly."

🌩️ Tweet Storm about how to use the latest AI and NLP techniques for note-taking, personal knowledge management, and productivity.

(from my newsletter going out tomorrow. Subscribe or read past issues online here)

getrevue.co/profile/bsunter briansunter.com/graph/#/page/n…

Graph Analysis

There are lots of graph theory techniques to analyze your notes..

Imagine a "social network" for Game of Thrones. You could see how "Daenerys" is related to "Jon Snow" and the other characters.

How to use #gpt3 for #gpt3poweredlearning like my machine learning study guide:

briansunter.com/graph/#/page/m…

1. Ask it to create a high level study guide:

"Write a curriculum for a ${type of person} to study ${topic}" 2. Ask it to create a study guide for each subtopic.

"Write a curriculum for ${type of person} to study the most important ${subtopic} concepts for ${topic}"