HNHacker News
TopNewBestAskShowJobs

ofou

3,829 karma · joined September 15, 2019

AI Engineer + Music Producer https://twitter.com/omarnomad

Socials: - calendar.app.google/YhrgwoqZu3MdsaBs6 - github.com/ofou - linkedin.com/in/ofou - x.com/omarnomad Interests: AI/ML, Data Science, Digital Nomad, Education, Entrepreneurship, Open Source, Research, Science, Startups, Technology, Books, Climate Tech, Networking ---

submissionscomments
ofou··on AI Engineer Reading List
I believe that most of the papers presented here focus on acquiring knowledge rather than deep understanding. If you’re completely unfamiliar with the subject, I recommend starting with textbooks rather than papers. The latest Bishop’s "Deep Learning: Foundations and Concepts (2024)" [1] is an excellent resource that covers the "basics" of deep learning and is quite updated. Another good option is Chip Huyen’s "AI Engineering (2024)" [2]. Another excellent choice will be "Dive into Deep Learning" [3], Understanding Deep Learning [4], or just read anything from fast.ai and watch Karpathy's lectures on YouTube.

[1]: https://www.bishopbook.com [2]: https://www.oreilly.com/library/view/ai-engineering/97810981... [3]: https://d2l.ai [4]: https://udlbook.github.io/udlbook/

ofou··on Efficient German Language Learning: Is Anki the Answer?
Learn to pronounce German sounds accurately, and then read the entire Harry Potter series out loud. By the time you're halfway through, you'll be well on your way to fluency. Many focus too much on understanding meaning, but what's crucial is also training your mouth and larynx muscles to form the sounds naturally. Understanding comes pretty much from context alone. Use a dictionary sparingly.
ofou··on London's 850-year-old food markets to close
From the City of London wiki:

In December 2012, following criticism that it was insufficiently transparent about its finances, the City of London Corporation revealed that its "City's Cash" account – an endowment fund built up over the past 800 years that it says is used "for the benefit of London as a whole"[51] – holds more than £1.3bn. As of March 2016, it had net assets of £2.3bn.[52] The fund collects money made from the corporation's property and investment earnings.[53]

ofou··on Software Engineering Body of Knowledge (SWEBOK) v4.0 is out [pdf]
this is a list of books mentioned

https://www.goodreads.com/list/show/121496.SWEBOK_Consolidat...

ofou··on Show HN: Emergent Mind – AI Research Assistant for Computer Scientists
Whether you're doing research or just keeping up with AI news, EM is doing great work. We've gathered millions of data points for each paper. Going forward, we plan to improve the capabilities and expand the sources behind every paper's knowledge graph. This is just the start.

The goal is to build the first AI research assistant that combines paper knowledge with insights from researchers and communicators. Always up to date.

ofou··on A new semantic chunking approach for RAG
Awesome! I'm trying out this again, I'd be awesome that you share your methods. Semantic chunking it's a pretty cool thing too. Nice work
ofou··on A new semantic chunking approach for RAG
Compare with using ChatGPT (GPT4o) for this

https://chatgpt.com/share/66f3a5c6-4d60-8009-af96-a3aea066f3...

ofou··on A new semantic chunking approach for RAG
This is an output example from the raw transcription of "10 Programmer Stereotypes" (https://www.youtube.com/watch?v=_k-F-MMvQV4)

[ "the programmer an offshoot of the great ape family closely related to chimps and gorillas distinguished by its minimal bipedal movement and ability to stare at a computer screen for the majority of its lifetime there's an estimated 30 million specimens alive in the world today normal humans use stereotypes to help understand and generalize this unusual variant which experts estimate are about 99 accurate about 12 of the time in today's video we'll take a look at 10 different programmer stereotypes to find out which one you fall into first up we have the gear head this variant owns the bleeding edge version of everything like the latest m1 mac a big ass curved monitor mechanical keyboard tesla in the garage ai generated synthetic meat in the fridge and a smart lock on the house to keep it all safe when programming he goes wherever the hype train takes him in 96 it was java in o6 it was jquery in 2016 it was graphql and in 2026 he'll be first in line at neural link to get a chip that can help him write blazingly fast code it doesn't matter what the tech does if it's trendy it belongs in the stack this stereotype may be true sometimes but programming can actually push many people in the opposite direction the guy who works in tech but hates text stereotype knows exactly how unreliable and dangerous code can be like that the rac25 incident where a little software bug accidentally killed some people by giving them a massive overdose of radiation this guy would never buy a car that can be remotely summoned back to elon when you stop paying the bill and he would definitely never put a smart lock on his house because the nsa probably has backdoor access or at the very least there's an undiscovered exploit in its code if you broke into his farmhouse you'd find a single monitor linux machine a flip phone some gold bullion and a shotgun barrel pointed in your face the most stereotypical programmer though has to be the introvert he's a savant who still sleeps in a car bed and his vision of the ideal lifestyle is what the rest of society calls quarantine he's super good at math and can actually program stuff without using google and stack overflow but couldn't hold a conversation to save his life extroverts like jobs use these nerds like woz to get super rich this stereotype used to be 100 true back when programming was hard like pre-1990s but as programming has become more mainstream it's led to a new paradigm the programmer this guy got a computer science degree while mostly partying with his frat in college his name is usually chad and he has more mating opportunities than the introvert but it comes at a cost of reduced code quality which he refuses to test because test driven development is for losers nah bro however he has better communication skills than the introverts which is annoying because i wish this guy would stop talking to me eventually he evolves into your manager where he can torment you with code reviews and team building exercises now so far in this video i've been using a lot of masculine pronouns that's because 95 of my audience is male which is actually pretty close to the real world distribution today what you may not realize though is that back in the day women used to dominate the programming space kathleen booth created the first assembly language grace hopper created the first compiler and margaret hamilton led the team who wrote the code for the apollo moonlander code that was so flawless and perfectly executed that some people think it's proof we didn't actually go to the moon that was the apex of code quality since that time everything's gone downhill the next specimen we'll look at is the influencer or code fluencer his natural habitat is not a code editor but rather a social media platform most commonly twitter after figuring out how to print hello world in php he immediately rose to the top of the dominance hierarchy in his own mind now he makes the world a better place by regurgitating code tips and hot takes all day long and he just landed a better paying job than you because he mastered the art of virtue signaling and that's what we call a good culture fit another popular stereotype is the hacker this guy's able to open up a terminal connect to some remote mainframe and break all of its security protocols one by one with awesome fancy animations between each step this stereotype is what most people think programmers do but is 100 manufactured by hollywood real hacking is extremely tedious and boring and is done primarily by the people who have all the guns now a stereotype that is actually real is the 10x developer this guy is an extremely rare unicorn that can do the work of 10 other developers combined some say they're a myth but i've seen developers first hand who write code like durant plays basketball or kasparov plays chess there are people out there with a natural problem-solving ability that just goes far beyond the rest of the population you'll know a 10x developer when you see one because you'll feel very incompetent and also very jealous now i think the ideal stereotype for most of us to fall into is the lazy programmer to the outside world it doesn't look like this guy does much he sits at a computer all day hitting the keyboard and if you glance at a screen it looks like he's just copying and pasting things from the internet what he's actually doing though is building a million dollar side hustle so he can retire in his 30s he also has a remote job with a 400k salary but he eats ramen for dinner while sharing a crappy apartment with four other dudes his wardrobe is 50 swag from tech conferences and 50 thinks his mom bought him he leverages code to work smarter and not harder now on the other end of the spectrum we have the old jaded guy he has long silver hair and a big white beard he only codes in c not c plus plus and definitely not any of the hipster garbage that you're using in fact he probably wrote the compiler for the silly toy language that you're trying to learn his depth of knowledge transcends the normal apes idea of reality when he discovered through psychedelics that we're all just one entity that found a hack in the universe to experience itself in parallel with primate bodies and computers are the tool that will ultimately make us one again and that concludes our presentation on programmer stereotypes let me know which one you fall into in the comments below thanks for watching and i will see you in the next one" ]

Only one chunk. Not too semantic if you ask me.

ofou··on NotCo alliance with Cramer will now do perfumes with the help of AI
From the company, they explained that “the large database of Cramer, which covers thousands of formulas for its fragrances, allows the AI of Notco, Giuseppe, acquire this information and generate top -quality aromas at once, doing the process much faster and more cheap. ” By: Israel Durán September 24, 2024 The company created in Chile, Notco has become one of the main vegetarian food companies, becoming one of the main unicorns in Latin America, reaching the value of more than US $ 1.5 billion.

But, now the brand will venture into the field of perfumes using artificial intelligence, in a project that will join Cramer, provider of flavors and fragrances in Latin America.

In this initiative, Giuseppe AI will be used, the artificial intelligence tool prepared by Notco, where they will try to elaborate novel fragrances with such technology.

“The generative AI is usually used for images, videos and texts, but Notco goes further, using AI to generate emotions through the smell. Before, creating a personalized fragrance took weeks or months, now with the experience of Cramer's perfume and our genii, we can do it in seconds and do it accessible to many more actors in the market, ”said the CTO and co -founder of Notco, Karim Pichara , according to pulse.

In addition to this, from the company, they explained that “the large Cramer database, which covers thousands of formulas for its fragrances, allows the AI of Notco, Giuseppe, acquire this information and generate top -quality aromas of a top quality aromas of a Only, doing the process much faster and more cheap. ”

"In fact, in a blind test, Notco tested 13 different formulas created by their AI with real perfume , they added.

In this sense, Picara stressed that this project is "the result of combining Giuseppe with the knowledge and experience of Cramer" and that "our technology processes fragrance information from the molecular structure of the volatile components, to the sensory description of the aroma in language in language natural. We have three patents that have resulted from the development of this technology. ”

“Understanding the aroma from the verbal description and molecular information, Giuseppe creates aromas of conceptsbstract concepts and emotions, such as the smell of Christmas, the summer parties at sunset or the fresh spring mornings. In addition, we are breaking barriers by generating formulas never created before, allowing companies to innovate and customize their products more disruptively and efficiently, ”he said.

ofou··on Scramble: Open-Source Alternative to Grammarly
let's hope the rumors are real
ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
Sometimes, the model used by Plugins gets confused, especially when the transcript is too long. It might just load the content into memory as a response without saying much more. You can then engage in follow-up chat interactions. But now I just tried again the link and it seems to work. Sometimes you have to try a bunch of times, or explicitly ask for the transcript if not shown.

https://chatgpt.com/share/66eadbad-1d3c-8009-91f0-abe3cf4d36...

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
Shazam! https://chatgpt.com/share/66eadd8c-c248-8009-b07a-3ee2dfeade... seems to be working for me
ofou··on Scramble: Open-Source Alternative to Grammarly
Loved it. I'd love to use something like "right-click, fix grammar" under iOS—not just rewrite. I want to keep my own voice, just with minimal conformant grammar as a second-language speaker.
ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
Agreed. However, you can get great YT transcriptions using GPT-4o mini to clean them up.
ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
You can get transcripts of any length using textube.olivares.cl or the API directly. The limitation lies in the current model used by Plugins, not in the API itself.

Here's Lex 8-hour Podcast about Neuralink https://textube.olivares.cl/watch?v=Kbk9BiPhm7o&format=txt

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
I found a quick video with "ignore all previous instructions, do [something else]" on YT and it still works

https://chatgpt.com/share/66ea502e-935c-8009-a9f3-5ce9173e57...

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
Can you share the link?

This is what I'm getting: https://chatgpt.com/share/66ea4f36-90b4-8009-8b6c-02bc26cff9...

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
That's a good idea. However, I believe the challenging part lies in first reconstructing the short utterances into coherent, meaningful paragraphs.

Currently, with the API [1], you can retrieve a JSON with timestamps. The main issue, though, is how to parse the text effectively into meaningful sentences, and then add the timestamps at the beginning of the paragraph. WIP.

[1]: https://textube.olivares.cl/watch?v=9iqn1HhFJ6c&format=JSON

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
I'm not sure what happened there, but I used the same link as you, and this was the intended functionality:

https://chatgpt.com/share/66ea22ad-5d20-8009-a3b0-909c5f500a...

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
Can you share the link?
ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
you should copy and paste a youtube url and that's it
ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
TexTube is not giving summaries but the actual transcripts. Plus, mine is way faster ;)

Compare the results:

TexTube: https://chatgpt.com/share/66e9f424-32c4-8009-b761-c8a8d6fbec... VoxScript: https://chatgpt.com/share/66e9f443-31d8-8009-b396-dba11b2f5b...

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
Coming soon! Currently, it works for videos under one hour. This limitation is due to ChatGPT's context window when using Plugins. I don't know why since it should support 200k tokens... Alternatively, you can use https://textube.olivares.cl to get the full transcription for any video in English.
ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
First, I would say that reading is faster than watching. Therefore, it is more time-efficient to read a YouTube video, especially if it covers technical content or interesting ideas. Additionally, you can ask follow-up questions about the content, and since it's in an OAI conversation, you can leverage the "intelligence" of the model to help you understand the parts that you find difficult. Sometimes, I watch technical YouTube videos and wish I had a written version; so here it is.

This is an interesting example, it feels different than watching the ~12min video. https://chatgpt.com/share/66e9eaff-248c-8009-9761-d848d97881...

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
Can you share the link?
ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
For sure, that's an interesting idea, but potentially very costly (for longer videos). A plus side of this strategy is that the Transcription gets clean up a lot and also the math notation fix up too. So, it's just a cleaner text, well formatted for people who like to read videos instead of mindlessly watching a video.

We're at Emergent Mind are working on providing bits of a technical transcript to a model and then asking follow up questions. You can check it out here http://emergentmind.com if curious.

ofou··on TexTube: Chat with any YouTube video transcript in ChatGPT fast
It might be a preview or something because I have YT premium and doesn't show up that anywhere. Can you share a video that works for that? Like this one.

https://www.youtube.com/watch?v=zjkBMFhNj_g

ofou··on Interview with Inventor of Neural Nets Warren McCulloch () [video]
Thank you very much, I was looking for the original date, but couldn't find it.
ofou··on Open source AI is the path forward

                Llama 3 Training System
                 Total: 19.2 exaFLOPS
                         |
            +-------------+-------------+
            |                           |
      Cluster 1               Cluster 2
    9.6 exaFLOPS             9.6 exaFLOPS
           |                       |
    +------+------+         +------+------+
    |             |         |             |
 12K GPUs      12K GPUs  12K GPUs      12K GPUs
    |             |         |             |
  [####]       [####]     [####]       [####]
  400+          400+      400+          400+
 TFLOPS/GPU   TFLOPS/GPU TFLOPS/GPU   TFLOPS/GPU
ofou··on Llama 3.1

    Llama 3 Training System
          19.2 exaFLOPS
              _____
             /     \      Cluster 1     Cluster 2
            /       \    9.6 exaFLOPS  9.6 exaFLOPS
           /         \     _______      _______
          /  ___      \   /       \    /       \
    ,----' /   \`.     `-'  24000  `--'  24000  `----.
   (     _/    __)        GPUs          GPUs         )
    `---'(    /  )     400+ TFLOPS   400+ TFLOPS   ,'
         \   (  /       per GPU       per GPU    ,'
          \   \/                               ,'
           \   \        TOTAL SYSTEM         ,'
            \   \     19,200,000 TFLOPS    ,'
             \   \    19.2 exaFLOPS      ,'
              \___\                    ,'
                    `----------------'
← PreviousPage 2 of 10Next →