3841
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 6,334 posts.
3842
How to use Alpaca-LoRA to fine-tune a model like ChatGPT
Low-rank adaptation (LoRA) is a technique for fine-tuning models that has some advantages over previous methods:
3843
Building a recommendation engine inside Postgres with Python and Pandas (2020)
Learn how you can leverage Python and Pandas from directly inside PostgreSQL to build your own recommendation engine.
3844
Adventures Building a Self-Driving RC Car
Having read some amazing books on Machine Learning, I had been looking for opportunities to apply ML from first principles in the real world. That was what got me curious about the wonderful Donkey Car project. The project is essentially a how-to guide to building your own RC car which can drive itself around a track…
3845
3846
3847
Circuit Tracing: Revealing Computational Graphs in Language Models (Anthropic)
We describe an approach to tracing the “step-by-step” computation involved when a model responds to a single prompt.
3848
LLMs and Code Optimization
Dave Andersen's (new) blog
3849
3850
Introduction to Monte Carlo Tree Search
The subject of game AI generally begins with so-called perfect information games. These are turn-based games where the players have no information hidden from each other and there is no element of chance in the game mechanics (such as by rolling dice or drawing cards from a shuffled deck). Tic Tac Toe, Connect 4…
3851
AI isn’t good enough
On a recent cross-country trip—I (Paul) drove from California to Illinois and back again.
3852
Nvidia’s AI supremacy is only temporary
Nvidia is an amazing company that has executed a contrarian vision for decades, and has rightly become one of the most valuable corporations on the planet thanks to its central role in the AI revol…
3853
The Alan Turing Institute has failed to develop modern AI in the UK
The UK’s flagship institute for artificial intelligence, the Alan Turing Institute, has been at best irrelevant to the development of modern AI in the UK.
3854
GPT-5 vs. Sonnet: Complex Agentic Coding
OpenAI released GPT-5 yesterday, promoting it as their best model yet for agentic coding.
3855
How AI is affecting productivity and jobs in Europe
Artificial intelligence promises to reshape economies worldwide, but firm-level evidence on its effects in Europe remains scarce. This column uses survey data to examine how AI adoption affects productivity and employment across more than 12,000 European firms. The authors find that AI adoption increases labour…
3856
I avoid using LLMs as a publisher and writer
Disclaimer: I am a book publisher & I love technology.
3857
I am frustrated with Stable Diffusion
I really want to make a game along the line of Myst. I have been collecting puzzles for years, and I have almost enough. I am flexible about the visual style. I’ve considered making sets out of lego, or cardboard , or cut paper. And I’ve considered AI-generated art.
3858
Pixel Visual Core: Google’s first custom-designed co-processor
Google’s first custom-designed co-processor for consumer products is built into every Pixel 2. Soon, it will enable more applications to use Pixel 2’s camera for taking …
3859
Fixing Tool-Call Accuracy in vLLM
Tool call accuracy is an important part of serving open-weight AI models. When your tool calls aren’t accurate, the model builds up on nonsensical context. We’ve been carrying our own fork of vLLM to hit 100% in tool call schema accuracy with Kimi and DeepSeek. Fortunately, vLLM 0.31 added support for constrained…
3860
Vibe-Coding a PCB – surprisingly good
I was expecting this to be pretty bad - but it actually came out quite nicely!
3861
IBM Patented Euler's 200 Year Old Math Technique for 'AI Interpretability'
IBM Slapped the Buzzwords 'AI Interpretability' on Generalized Continued Fractions and their Series Transformations and was awarded a Patent
3862
Learnings from building AI agents
How cubic reduced noisy AI code review comments with reasoning logs, fewer tools, specialized agents, and evaluation before changes reached production.
3863
Matrix Multiplications on GPUs Run Faster When Given “Predictable” Data (2024)
Great minds discuss flops per watt.
3864
New chips for machine intelligence
This note summarises details of some of the new silicon chips for machine intelligence. Its aim is to distil the most important implementation and architectural details (at least those that are currently available), to highlight the main differences between them. I’m focusing on chips designed for training since they…
3865
Self-flying drone dips, darts and dives through trees at 30 mph
A researcher from MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) has developed an obstacle-detection system that allows a drone to autonomously dip, dart and dive through a tree-filled field at upwards of 30 miles per hour.
3866
Animate Anyone 2: High-Fidelity Character Image Animation
Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance
3867
3868
Vectors are over, hashes are the future
Get an introduction into the thinking behind the rise of neural hashing technology — and learn why this may end up being an enormous shift in AI advancement.
3869
Moonshine, the new state of the art for speech to text
Can you imagine using a keyboard where it took a key press two seconds to show up on screen? That’s the typical latency for most voice interfaces, so it’s no wonder they’ve failed…
3870
Asylo: an open-source framework for confidential computing
Protecting data is the number one consideration when running workloads in the cloud. While cloud infrastructures offer numerous security controls, some enterprises want additional verifiable isolation for their most sensitive workloads—capabilities which have become known as confidential computing. Today we’re excited…