2911
Building SQLite with a small swarm
Yes, for a supported subset of SQL. To establish a baseline, I integrated the SQLLogicTest suite.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 3,092 posts.
2912
Stop saying that AI is just a tool and it only matters how it is used
I’m tired of this phrase and this simple way of thinking about tools. This blog post is a wandering train of thought on the topic of what tools are and why it matters to be even slightly more mature in how we think about them.
2913
Why Can a Machine Beat Mario but Not Pokemon?
Why Can a Machine Beat Mario but not Pokemon? By now, you’ve probably heard of bots playing video games at superhuman levels. These bots can be programmed explicitly, reacting to set inputs with …
2914
A new AI game: Give me ideas for crimes to do
Less than a week ago OpenAI unleashed ChatGPT on the world, and it kicked off what feels like a seismic shift in many people’s understand of the capabilities of large …
2915
2916
Untrusted chatbot AI between you & the internet is a disaster waiting to happen
JavaScript, math, maps, etc
2917
2918
Hacking Your Own AI Coding Assistant with Claude Pro and MCP
Reverse Engineering Reality
2919
2920
"Building Machines That Learn and Think Like People", 7 Years Later
In the post about GPT-4V, I mentioned the paper “Building Machines That Learn and Think Like People” (https://arxiv.org/abs/1604.00289) by Brenden Lake, Tomer Ullman, Joshua Tenenbaum, and Samuel Gershman.
2921
Claude Opus 5.5 Can Draw Permit-Level Architectural Drawings
I tested thirteen models and found that their drafting is approaching professional levels.
2922
A polynomial autoencoder beats PCA on transformer embeddings
A closed-form autoencoder: PCA encoder + quadratic Ridge decoder. On FiQA it gives 4× compression of mxbai-embed-large-v1 at -0.88 p.p. NDCG@10, +1.34 p.p. over PCA. No SGD, no neural networks.
2923
Building an IBM Watson-powered AI Chatbot in 50 lines of code
Developing a speech-to-text bot using IBM’s Supercomputer.
2924
Understanding LSTM Networks (2015)
Humans don’t start their thinking from scratch every second. As you read this essay, you understand each word based on your understanding of previous words. You don’t throw everything away and start thinking from scratch again. Your thoughts have persistence.
2925
2926
2927
ProfileGPT: An Example of AI Agents Collaboration Architecture
A dive into the architecture and design of ProfileGPT, an app that allows users to analyze their user's profile and personality as seen by ChatGPT to raise awareness about data usage.
2928
When Greedy Algorithms Are Good Enough (2014)
Greedy algorithms are among the simplest and most intuitive algorithms known to humans. Their name essentially gives their description: do the thing that looks best right now, and repeat until nothing looks good anymore or you’re forced to stop. Some of the best situations in computer science are also when greedy…
2929
Deep Language Modeling for Question Answering Using Keras
Search BenchGecko research notes, methodology pages, benchmark sources, model rankings, pricing, compute, and company intelligence.
2930
A round-up of topology-based papers at ICML 2020
With this year’s International Conference on Machine Learning (ICML) being over, it is time to have another instalment of this series. Similar to last year’s post , I shall cover several papers that caught my attention because of their use of topological concepts—however, unlike last year, I shall not restrict the…
2931
Keras and deep learning on the Raspberry Pi
In this guide you'll learn how to perform real-time deep learning on the Raspberry Pi using Keras, Python, and TensorFlow.
2932
Deep Learning in Rust
Meta Edit 2/2/2016: I wrote this post when deeplearn-rs was only a week old. This is more of a journal post where I reflect on things. To…
2933
Notes on Cruise's Pedestrian Accident
This is a set of notes on the Quinn Emanuel report on Cruise's handling of the 2023-10-02 accident where a Cruise autonomous vehicle (AV) hit a pedestrian, stopped, and then started moving again with the pedestrian stuck under the bottom of the AV, dragging the pedestrian 20 feet. After seeing some comments about this…
2934
Nvidia's CUDA Monopoly
CUDA (Compute Unified Device Architecture) is a closed-source low-level API that interfaces software with NVIDIA GPUs.
2935
Why are coding agents so dumb?
Models are getting better and better, while the agents that drive them languish.
2936
AI made coding more enjoyable
To me, one of the most annoying parts of software engineering is writing code that doesn’t require thinking. It’s just a typing exercise, and that’s boring.
2937
Claude Code feels like magic because it is iterative
Personal blog of Omar Abid
2938
Using Claude Code SDK to reduce E2E test time
Best of both worlds: Building an AI gatekeeper that knows exactly which tests to run for your code changes
2939
LLM Networking with MikroTik
I’ve been refraining from saying ‘vibe networking’ or ‘vibkrotik’ or some other abomination, but it is true - I have been using LLMs to setup a few networks these last few months, and things have generally gone over swimmingly.
2940
The Neural Net Tank Urban Legend
AI folklore tells a story about a neural network trained to detect tanks which instead learned to detect time of day; investigating, this probably never happened.