1711
AI agent benchmarks are broken
Benchmarks are foundational to evaluating the strengths and limitations of AI systems, guiding both research and industry development.
Topics /
AI & Machine Learning
The most popular blog posts about ai & machine learning on Hacker News. 3,091 posts.
1712
The Future of MCPs
MCPs—Model Context Protocols—are set to transform AI from passive chatbots into powerful, action-taking agents. But the real story isn’t what MCPs enable—it’s who controls them.
1713
Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do
Give any AI agent a persistent memory in minutes. Works with Claude, ChatGPT, Ollama, OpenRouter, and any MCP-compatible agent. Open source, self-hosted, model-agnostic.
1714
What is GPT-3? written in layman's terms
Daily, snackable writings to spur changes in thinking. Building a blueprint for a better brain by tinkering with the code.
1715
1716
A guide to prompting AI, for what it is worth
A little bit of magic, but mostly just practice
1717
Build your own Siri locally and on-device
That doesn’t spy on you
1718
A visual exploration of vector embeddings
For Pycon 2025, I created a poster exploring vector embedding models, which you can download at full-size . In this post, I'll translate ...
1719
Emergent Features in 6.7B+ Param Transformers
When I attended NAACL, I wanted to do a little test. I had two pitches for my LLM.int8() paper. One pitch is about how I use advanced quantization methods to achieve no performance degradation transformer inference at scale that makes large models more accessible. The other pitch talks about emergent outliers in…
1720
1721
AI Responses May Include Mistakes
The other day I wanted to look up a specific IBM PS/2 model, a circa 1992 PS/2 Server system. So I punched the model into Google, and got this:
1722
AI and the Ship of Theseus
Slopforks: what happens when a library gets rewritten with AI?
1723
Softmax forever, or why I like softmax
[UPDATE: Feb 8 2025] my amazing colleague Max Shen noticed a sign mistake in my derivation of the partial derivative of the log-harmonic function below.
1724
Hacker News, Sans AI
I like HackerNews, but I don't love that so much of it has turned into discussion of a single topic: AI. This is a version of HackerNews, filtered to remove any article focusing on __AI__. Refreshes about every ten minutes.
1725
Why Bayesian Stats Needs Monte-Carlo Methods
Bayesian statistics rely heavily on Monte-Carlo methods. A common question that arises is “isn’t there an easier, analytical solution?” This post explores a bit more why this is by breaking down the analysis of a Bayesian A/B test and showing how tricky the analytical path is and exploring more of t
1726
The skill of the future is not 'AI', but 'Focus'
Don't let AI erode your focus.
1727
Coping with dumb LLMs using classic ML
Taking the output of many dumb LLM search relevance judges and feeding the output to a decision tree to improve precision
1728
1729
ML Beyond Curve Fitting: An Intro to Causal Inference and Do-Calculus
Since writing this post back in 2018, I have extended this to a 4-part series on causal inference: * ➡️️ Part 1: Intro to causal inference and do-calculus [https://www.inference.vc/untitled] * Part 2: Illustrating Interventions with a Toy Example…
1730
The RWKV language model: An RNN with the advantages of a transformer
I explain what is so unique about the RWKV language model.
1731
Logistic Regression from Bayes’ Theorem
In this post we’ll explore how we can derive logistic regression from Bayes’ Theorem. Starting with Bayes’ Theorem we’ll work our way to computing the log odds of our problem and the arrive at the inverse logit function. After reading this post you’ll have a much stronger intuition for how logistic
1732
1733
Deep code search
Deep code search Gu et al., ICSE’18 The problem with searching for code is that the query, e.g. “read an object from xml,” doesn’t look very much like the source code snippets tha…
1734
Intuitively Understanding Harris Corner Detector
If you ever tried to learn how the Harris corner detection algorithm works, you might have noticed that the process is not intuitive at all. First, you start with an energy function, approximate it using Taylor approximation, get a matrix from that, then find the eigenvalues of that matrix, etc. But when you come to…
1735
Unexpected Consequences of Self-Driving Cars
Many new technologies have unexpected impacts on the physical or social world in which we live.
1736
AI Angst
My input stream is full of it: Fear and loathing and cheerleading and prognosticating on what generative AI means and whether it’s Good or Bad and what we should be doing. All the channels: Blogs and peer-reviewed papers and social-media posts and business-news stories. So there’s lots of AI angst out there, but this…
1737
The case against Google's claims of "quantum supremacy"
The 2019 paper “Quantum supremacy using a programmable superconducting processor” asserted that Google’s Sycamore quantum computer, with 53 qubits and a depth of 20, performed a specific computat…
1738
I'm the AGI that's wiping out humanity
Alex Moon is an Australian-British software engineer and artist based in the North East of England.
1739
How does cosine similarity work?
Cosine similarity measures the angle between two vectors — the dot product divided by the product of their magnitudes. Here's what each part of the formula does.
1740