Patterns and problems in emerging multi-agent systems
We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage. Here, we share what they mean for AI safety.
Topics /
The most popular blog posts about software engineering on Hacker News. 1,413 posts.
We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage. Here, we share what they mean for AI safety.
We replaced LibDOM with a custom Zig implementation for better cohesion across events, Custom Elements, and ShadowDOM. Here's how we built it and what we learned along the way.
So, you want to improve the performance of your deep learning model. How might you approach such a task? Often, folk fall back to a grab-bag of tricks that might've worked before or saw on a tweet. "Use in-place operations! Set gradients to None! Install PyTorch 1.10.0 but not 1.10.1!"
Matyáš Racek's blog
Rahul's Blog
TruffleRuby started as my internship project at Oracle Labs in early 2013. It is an implementation of the Ruby programming language on the JVM, using the Graal dynamic compiler and the Truffle AST interpreter framework . TruffleRuby can achieve peak performance well beyond that possible in JRuby at the same time as…
Sticks tongue out at AI
Tiger Style and matklad recommend pushing ifs up and fors down. This post looks at what the idiom actually says, where it shows up in query optimization and in the algebra of functional programs, and where the analogy stops paying for itself.
Learnings from post-AI Open Source and how we’re approaching this so far.
Large DELETEs add work instead of reclaiming it. Structure your database so deletion becomes DROP TABLE or TRUNCATE.
Introducing Elena, a simple, tiny library for building Progressive Web Components.
AI helping pharmaceutical researchers query decades of information buried in PDF reports
Type systems verify properties of programs. Production correctness is a property of systems. The gap between these is where the interesting failures live.
I’ve been tinkering around with Zig to explore what’s possible with comptime. Whenever I evaluate a new language I use three axes:
What extra stuff is needed to properly run a language model? Besides the weights of a language model, what is the gguf metadata that we need to parse and use?
🏠🏠🏠🌲🌲🌲🏠🌲🌲🏠🌲🌲🏠🌲🏠🌲❌🏠🌲🌲🌲
Pandas has taken us a long way, but it's time for a new bear
Interestingly enough, at least two of them were specifically about performance!
Exploring tail-call-style interpreter implementation with an optimized Uxn emulator, on ARM, x86, and WebAssembly
A few months ago I became obsessed with a silly question: why does my Emacs, on a laptop with a perfectly capable GPU, draw all of its text using the…
That morning I woke up at 6:58, two minutes before the alarm. I lay there and waited for it to ring. And it rang. We both did our jobs. I still don’t know why I remember it in such detail. I used to forget what I’d had for dinner the night before. And now I remember the whole morning minute by minute, as if someone…
My Implementing a Forth article got some great feedback, particularly around the subject of tiny Forth implementations. (And it was an excuse to list some of the tiniest Forths I’ve seen.)
Stripe Across is a grog. We hope you enjoy it.
When I started programming, my whole day revolved around development. I’d wake up, write code, and go to sleep. And that’s how it was day in and day out. My entire social circle consisted of people who also wrote code. I studied frameworks, libraries, and various programming languages.
In the past few months, I’ve been stress-testing how far AI coding agents can take us when building real, production-grade distributed systems. The result: a Rust-based multi-Paxos consensus engine that not only implements all the features of Azure’s Replicated State Library (RSL) [1] — which underpins most major…
Co-authored-by: ur mom
Let’s say you’re creating a CLI tool which has to display syntax highlighted source code. You begin by choosing some colors which look nice with your chosen terminal theme:
Memoryfields - a vastly simpler way to do agent memory
When a codebase is large and complex, it's risky to big changes. Here's a structured way to approach