151
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 673 posts.
152
Anthropic Claude 3.5 can create icalendar files, so I did this
Generate calendar entries from an image using Anthropic Claude 3.5. Convert lesson dates in an image to a calendar ICS file
153
Microsoft is spying on users of its AI tools
Microsoft announced that it caught Chinese, Russian, and Iranian hackers using its AI tools—presumably coding tools—to improve their hacking abilities. From their report: In collaboration with OpenAI, we are sharing threat intelligence showing detected state affiliated adversaries—tracked as Forest Blizzard, Emerald…
154
Kalman Filter Explained Simply
Tired of equations and matrices? Ready to learn the easy way? This post explains the Kalman Filter simply with pictures and examples!
155
Postgres.new: In-browser Postgres with an AI interface
Introducing postgres.new, the in-browser Postgres sandbox with AI assistance.
156
Amazon Nova
Amazon Nova foundation models deliver frontier intelligence and industry leading price-performance, with support for text and multimodal intelligence, multimodal fine-tuning, and high-quality images and videos.
157
Video generation models as world simulators
We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our…
158
159
Representation Engineering: Mistral-7B on Acid
Playing around with the Representation Engineering paper, I made some interesting control vectors, and a Python package to make your own.
160
Meta's new LLM-based test generator
Meta's TestGen-LLM is a sneak peek to the future of developer productivity: specialized, orchestrated, and rigorously filtered.
161
A ChatGPT mistake cost us $10k
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...
162
Building an LLM from Scratch: Automatic Differentiation (2023)
Automatic Differentiation
163
Google's First Tensor Processing Unit: Architecture
Looking in more detail at Google's first Tensor Processing Unit
164
Testing Generative AI for Circuit Board Design
An article studying the use of LLMs fror designing circuit boards
165
166
A ChatGPT clone, in 3000 bytes of C, backed by GPT-2 (2023)
This program is a dependency-free implementation of GPT-2, including byte-pair encoding and transformer inference, in ~3000 bytes of C. I then use this to create something like Chat GPT.
167
Claude's API now supports CORS requests, enabling client-side applications
Anthropic have enabled CORS support for their JSON APIs, which means it’s now possible to call the Claude LLMs directly from a user’s browser. This massively significant new feature is …
168
Fast LLM Inference From Scratch (using CUDA)
This post is about building an LLM inference engine using C++ and CUDA from scratch without libraries.
169
The OpenAI board was right
Even on little things, Sam is not consistently candid.
170
171
NotebookLM launches feature to customize and guide audio overviews
NotebookLM is piloting a way for teams to collaborate, and introducing a new way to customize Audio Overviews.
172
How Does GPT-4o Encode Images?
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…
173
My Python code is a neural network
This post translates a Python program to a recurrent neural network. It visualizes the network and explains each step of the translation in detail.
174
175
OpenAI’s board, paraphrased: ‘All we need is unimaginable sums of money’
OpenAI is to this decade’s generative-AI revolution what Netscape was to the 1990s’ internet revolution.
176
Sharing new research, models, and datasets from Meta FAIR
Meta FAIR is releasing new research artifacts that highlight our recent innovations in developing agents, robustness and safety, and architectures that facilitate machine learning.
177
178
A Student's Guide to Writing with ChatGPT
Discover how students can use ChatGPT for writing, research, studying, and editing. Learn practical tips for using AI responsibly in school and beyond.
179
YC is wrong about LLMs for chip design
LLMs don’t make chips better. Good engineers do.
180
Probably pay attention to tokenizers
Last week I was helping a friend of mine to get one of his new apps off the ground. I can’t speak much about it at the moment, other than like most apps nowadays it has some AI sprinkled over it. Ok, maybe a bit maybe more just a bit – depends on the way you look at it, I suppose. There is a Retrieval-augmented…