The latest blog posts to take off on Hacker News. 3,091 posts.
If you read my previous blog post, you probably already know that I like my smart home open-source and very local, and that certainly includes any voice assistant I may have. If you watched the video demo, you have probably also found out that it’s… slow. Trust me, I did too. Prefix caching helps, but it feels like…
Apple Intelligence makes a lot of sense when you get out of the AI bubble. Plus, the cool technical details Apple shared about their language models "thinking different."
I discuss why Alexa missed the opportunity to take the lead and become the dominant player in the conversational AI market.
Edit: I want to preface this by saying yes the practices here are very bad and embarrassing (and we've since added robust unit/integration tests and alerting...
how developmental biology might contain the secrets to life, intelligence, and immortality
A metascience post of sorts that argues we should take human capital more seriously
Here’s a fact: GPT-4o charges 170 tokens to process each 512x512 tile used in high-res mode. At ~0.75 tokens/word, this suggests a picture is worth about 227 words—only a factor of four off from the traditional saying. (There’s also an 85 tokens charge for a low-res ‘master thumbnail’ of each picture and higher…
Generative Adversarial Networks (GANs), discovered by Ian Goodfellow in 2014, were an early method in the area of generative AI. I will focus on image generation as set out in the paper Generative Adversarial Nets 1 . This paper is the focal point of the post, I will guide you through the implementation of the paper…
This article will be part of an extensive series in which I plan to explore various aspects of Fourier Mathematics. I will take notes, create some visuals (a good pretext to learn more about graphics), and hope that it will be helpful to anyone looking for a clear, visual introduction to these concepts. The article…
How AI hype leads to flawed research that fuels more hype
Homepage of Tri Dao.
Posted on Friday 31 May 2024. 2,785 words, 28 links. By Matt Webb.
A path to continued model improvement.
I’m coding a system in JavaScript that generates sentences of “meaningful nonsense”. Here are some examples.
I’m beginning to suspect that one of the most common misconceptions about LLMs such as ChatGPT involves how “training” works. A common complaint I see about these tools is that …
Link to: https://www.nytimes.com/2024/05/24/technology/google-ai-overview-search.html
I spent 2022 learning to draw and was blindsided by the rise of AI art There is lots to say about this, whether it has been or will be a good thing for artists and society in the long run. I hope to write about it in another post. models like Stable Diffusion. Suddenly, the computer was a better artist than I could…
Discover systematic strategies to enhance your Retrieval-Augmented Generation (RAG) systems for better performance and user experience.
Buying fake William Morris prints on Etsy and other early signs of epistemological collapse
Xe Iaso's personal website.
Note: In my last newsletter, I said that my next post would be the second part of my Facebook autopsy. Don’t worry, that’s still coming, but given the recent drama between Sam Altman, OpenAI, and Scarlett Johansson, I felt the need to write something. Don’t worry, I
Even on little things, Sam is not consistently candid.
👯 On training my own AI to steal illustrators’ styles
A shift toward products and a research brain drain should ring your alarm bells
Thanks for HN users mik1998 and borodi who brought up the popcnt instruction and the count_ones function in Julia which carries this out, I've updated the timings and it's even faster now.
Protein “language” is a lot like human language. Given the similarities, researchers have been building and training language models on protein sequence data, replicating the success seen in other domains, with profound implications. In this post, I will explore how transformer models have been applied to protein data…
