My LLM codegen workflow

my-llm-codegen-workflow

tl:dr; Brainstorm spec, then plan a plan, then execute using LLM codegen. Discrete loops. Then magic. ✩₊˚.⋆☾⋆⁺₊✧ I have been building so many small products using LLMs. It has been fun, and useful. However, there are pitfalls that can waste so much time. A while back a friend asked me how I was using LLMs […]

Nuclear fusion: WEST beats the world record for plasma duration

nuclear-fusion:-west-beats-the-world-record-for-plasma-duration

​1,337 seconds: that was how long WEST, a tokamak run from the CEA Cadarache site in southern France and one of the EUROfusion consortium medium size Tokamak facilities, was able to maintain a plasma for on 12 February. This was a 25% improvement on the previous record time achieved with EAST, in China, a few weeks […]

Tensor Evolution: A Framework for Fast Evaluation Using Recurrences

tensor-evolution:-a-framework-for-fast-evaluation-using-recurrences

Abstract:This paper introduces a new mathematical framework for analysis and optimization of tensor expressions within an enclosing loop. Tensors are multi-dimensional arrays of values. They are common in high performance computing (HPC) and machine learning domains. Our framework extends Scalar Evolution – an important optimization pass implemented in both LLVM and GCC – to tensors. […]

Pi-hole v6

pi-hole-v6

We’re excited to announce the general release of Pi-hole v6! At a glance: What’s New in Pi-hole v6? 1. Embedded Web Server and REST API We’ve integrated a new REST API and embedded web server directly into the pihole-FTL binary. This eliminates the need for lighttpd and PHP, reducing the installation footprint and boosting performance. […]

Among top researchers 10% publish at unrealistic levels, analysis finds

among-top-researchers-10%-publish-at-unrealistic-levels,-analysis-finds

About 10% of the most influential researchers worldwide in various scientific fields, including chemistry, are achieving ‘implausibly high’ publication and new co-author rates. Many are producing hundreds of papers each year and gaining hundreds to thousands of new collaborators annually, according to recent analysis by researchers at King Fahd University of Petroleum and Minerals in […]

Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs

Hi HN! I’m Prithvi, and my co-founder Frances and I built Promptless (https://gopromptless.ai), an AI teammate that proactively updates docs while you ship software. There’s a demo video at https://youtu.be/pmslSl8dOgE, and also a “Live Demo on Your Own Docs” at https://gopromptless.ai/demo where you can plug in the URL to any existing docs site and simulate […]

Try Thinking and Learning Without Working Memory (2008)

try-thinking-and-learning-without-working-memory-(2008)

Imag­ine dial­ing a phone num­ber by hav­ing to look up each dig­it one at a time in the phone book. Nor­mal­ly, you look up the num­ber and remem­ber all sev­en dig­its long enough to get it dialed. Even with one dig­it at a time, you would have to remem­ber each dig­it long enough to get […]

One year after switching from Java to Go

one-year-after-switching-from-java-to-go

I always told people memory is cheap, black magic is OK and efficiency doesn’t matter in most cases, but boy, how wrong was I… My Java journey started back in 2011 (14 years ago – wow) when I started studying computer science at the Vienna University of Technology. Using editors like jEdit and compiling my […]

Svelte 5 is not JavaScript

svelte-5-is-not-javascript

For the last couple of weeks, I’ve been dealing with the fallout of upgrading a web application to Svelte 5. Complaints about framework churn and migration annoyances aside, I’ve run into some interesting issues with the migration. So far, I haven’t seen many other people register the same issues, so I thought it might be […]