Hacker Newsnew | past | comments | ask | show | jobs | submit | more lovestory's commentslogin

Seems like "Uber for X" turned into "Cursor for X".


Using AI to develop novel drugs. Imagine the world without or with minimal diseases. Only one can hope.


Or just make a new kind of heroin


While tools like NotebookLM and Perplexity are impressive and highly effective for conducting research on any topic/query, SurfSense elevates this capability by integrating with your personal knowledge base. It is a highly customizable AI research agent, connected to external sources such as search engines (Tavily, LinkUp), Slack, Linear, Notion, YouTube, GitHub, Discord and more to come.


Here in the Balkans and most of European countries always have public squares or similar gathering place for each neighborhood. I was shocked when I visited some USA states that absolutely have nothing of that sort. Not even a park that is tailored for a few hours hangout sessions. Even some public spaces like parks and library gardens are filled with corporate interests like Starbucks. You absolutely are expected to spend money whenever you go out which is depressing af.


This is a few days worth of materials to read. If anyone finds it overwhelming, I recommend you read this comic that teaches you the basics of idea behind spaced repetition https://ncase.me/remember/


My personal workflow with memorizing with Anki using LLMs is as follows: Read textbook material first. It's important that you understand what you are learning.You cannot just breakdown information into atoms and expect to understand how it works together (for example: you can learn that there are monounsaturated fats, polyunsaturated fats, saturated fats and trans fats. But without reading beforehand about them from a textbook or other source, you will not understand how they differ (in chemical structure, biological function etc). After I understand the material, I feed LLM the documents (textbooks etc) and give it the following prompt: >I want to generate flashcards from the provided textbook document using the attached PDF. Each flashcard should contain a question and a corresponding answer formatted as pairs in plaintext code block. The structure should be: "Question","Answer" >Extract key concepts, definitions, and explanations from the textbook. If in the text imperial unit system is used, convert it to metric. For mathematical symbols and equations, format them using inline MathJax syntax because I will be importing the copied text to Anki. Ensure questions are clear and concise while answers provide a direct yet comprehensive response.

After the text is generated, I check out the accuracy (in 95% of cases the cards are accurate) and I import them into my decks. The rest is good old school Anki memorizing.


I remember trying that a few months back but I was not convinced by the quality of the cards. It's also hard to convey what I think a good card is, I guess there's something about not getting lost in the details while missing the big picture.

You only commented on accuracy, but what's your experience on relevance and how useful LLM-generated flashcards are?

To be clear I've already found myself deleting some flashcards I made myself while reviewing them when I realized they were bad, so I guess one can do that for LLM-generated questions as well, as long as the irrelevance rate is somewhat similar.


Well I can give you an output example. This was generated based on chapter from textbook about Vitamin (Vitamin D in this example)

"Which nutrient can be synthesized by the body using sunlight?","Vitamin D" "What is the primary role of vitamin D in calcium regulation?","Raises blood calcium by enhancing absorption, mobilizing bone stores, and reducing kidney excretion" "How does vitamin D affect bones?","Supports bone mineralization and integrity" "What form does vitamin D take before activation?","Inactive precursor synthesized in the skin or consumed in diet" "Which organs activate vitamin D?","Liver and kidneys" "What are signs of vitamin D deficiency in children?","Bowed legs and bone deformities (rickets)" "What is osteomalacia?","Soft, weak bones in adults due to vitamin D deficiency" "What disease is caused by long-term vitamin D deficiency in adults?","Osteoporosis" "How does vitamin D deficiency affect older people?","Increases risk of fractures and joint pain" "What is the toxic effect of too much vitamin D?","Calcification of soft tissues"

You get the idea. How would you rate it's usefulness is subjective but it gets the job done.


I have been looking for a workflow to do exactly this!

Which LLM do you use?

Do you do anything special to structure the deck by chapter or section?


Yes I use tags and then I display the tag using CSS at the bottom of each question. You can find out how to do this from anki manual. EDIT: this is useful because sometimes different chapters will contain similar questions but with the focus on different answer (for example: when studying trigonometry and when studying derivative of a function, similar questions will be present so you will need tags to guide you towards the answer).


Even Katy Perry started using AI for her tour backdrop visuals and it looks... well, horrendous https://twitter.com/bklynb4by/status/1915514396421337171


Will this allow for more bluetooth options? For example connecting with bluetooth page turner would be a killer feature, but so far Kindle only allows for audio transfers via bluetooth.


https://www.notboring.co/ Probably not new for most of people here but it's a breath of fresh air


Don't bother with this one - the latest post (The Return of Magic) is promoting a load of unscientific woo (The Telepathy Tapes). The author seems to seriously mean the title of the post literally.


I started reading the first half of that. I definitely sense what you’re sensing but I’m curious, what is it that you object to specifically?


Basically his whole "return of magic" premise seems to be rooted in his listening to "The Telepathy Tapes" and it confirming/supporting some of his latent beliefs. But the Telepathy Tapes is utter nonsense and self delusion based on wishful thinking and the "Autism Parent" movement.

https://www.theamericansaga.com/p/the-telepathy-tapes-is-tak...


Unless you don't mind round the clock air pollution, violation of human rights, hybrid political regimen (not a democracy) and coruptation in every public instutiton, then yeah it can be pretty okay place for a family


https://aqicn.org/map/belgrade/ It's not great air quality, but round the clock air pollution is a great exaggeration.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: