1981
Agentic Coding Recommendations
Current recommendations of agentic coding.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 6,326 posts.
1982
False memory implantation in adults is easy
false memory implantation in adults is easy (bonus: here's one way to do it)
1983
Using a Keras Long Short-Term Memory Model to Predict Stock Prices
Editor’s note: This tutorial illustrates how to get started forecasting time series with LSTM models. Stock market data is a great choice for this because it’s quite regular and widely available to everyone. Please don’t take this as financial advice… Continue reading Using a Keras Long Short-Term Memory (LSTM) Model…
1984
Want to spot a deepfake? Look for the stars in their eyes
In an era when the creation of artificial intelligence (AI) images is at the fingertips of the masses, the ability to detect fake pictures – particularly deepfakes...
1985
1986
Face swapping with Python, dlib, and OpenCV
In this post I’ll describe how I wrote a short (200 line) Python script to automatically replace facial features on an image of a face, with the facial features from a second image of a face.
1987
Compiling a neural net to C for a speedup
A cozy little corner of the web.
1988
AI produces realistic sounds that fool humans
A video-trained system from MIT’s Computer Science and Artificial Intelligence Lab could help robots understand how objects interact with the world.
1989
Where is Noether's principle in machine learning?
Physics likes optimization! Subject to its boundary conditions, the time evolution of a physical system is a critical point for a quantity called an action. This point of view sets the stage for Noether's principle , a remarkable correspondence between continuous invariances of the action and conservation laws of the…
1990
1991
A misleading open letter about sci-fi AI dangers ignores the real risks
Misinformation, labor impact, and safety are all risks. But not in the way the letter implies.
1992
MCP is dead; long live MCP
Understanding the social media zeitgeist around CLIs and the premature death of MCP
1993
Stochastic gradient descent written in SQL
Edit – this post generated a few insightful comments on Hacker News. I’ve also put the code in a notebook for ease of use. Introduction Modern MLOps is complex because it involves too many components. …
1994
Designing NotebookLM
Designer, builder, and visual storyteller. Now building Huxe. Previously led design on NotebookLM and contributed to Google AI projects like Gemini and Search. Also shoot photo/video for brands like Coachella, GoPro, and Rivian.
1995
1996
1997
Use GPT-3 incorrectly: reduce costs 40x and increase speed by 5x
Cosine trains AI models and specialised coding agents for organisations that need frontier capability within secure environments.
1998
Understanding Transformers Using a Minimal Example
Visualizing the internal state of a Transformer model
1999
Text Is All You Need
Personhood appears to be simpler than we thought
2000
OpenAI Privacy Filter
OpenAI Privacy Filter is an open-weight model for detecting and redacting personally identifiable information (PII) in text with state-of-the-art accuracy
2001
Introduction to Decision Tree Learning
From Kaggle to classrooms, one of the first lessons in machine learning involves decision trees. The reason for the focus on decision trees is that they aren’t very mathematics heavy compared to other ML approaches, and at the same time,… Continue reading Introduction to Decision Tree Learning
2002
Why do we need human mathematicians anymore?
[This is a guest post by Po-Shen Loh, crossposted from his blog, where an illustrated version appears. This blog post was initially written in a different file format and converted using AI. —…
2003
Bard is getting better at logic and reasoning
Two improvements are launching in Bard to help you get more accurate responses and export to Google Sheets.
2004
Certified 100% AI-free organic content
This is a last call to introduce a "made by an organically-sourced human" label.
2005
Inkling 2 Small
Today we are introducing the second generation of Inkling models with the release of Inkling 2 Small.
2006
Auto mode is now the default in Claude Code
Claude Code will soon run auto mode by default for Pro, Max, Ultra, and Team plans, enabling longer-running autonomous work, and catching more dangerous commands.
2007
We should revisit literate programming in the agent era
Literate programming is the idea that code should be intermingled with prose such that an uninformed reader could read a code base as a narrative, and come away with an understanding of how it works and what it does. Although I have long been intrigued by this idea, and have found uses for it in a couple1 of different…
2008
Pac-Man recreated with a GAN trained on 50k game episodes
Bringing together the world’s brightest minds and the latest accelerated computing technology leads to powerful breakthroughs that help tackle some of the biggest research problems....
2009
RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8
Dual GPU setup: run Qwen 3.6 27B at a Q8 quantization at 80+ tokens/sec with 39GB total VRAM
2010
Making Visible Watermarks More Effective
Posted by Tali Dekel and Michael Rubinstein, Research ScientistsWhether you are a photographer, a marketing manager, or a regular Internet user, ch...