Agents need control flow, not more prompts
Thesis: reliable agents tackling complex tasks need deterministic control flow encoded in software, not increasingly elaborate prompt chains If you’ve eve...
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 21,816 posts.
Thesis: reliable agents tackling complex tasks need deterministic control flow encoded in software, not increasingly elaborate prompt chains If you’ve eve...
Today marks a huge milestone for us - the first public release of Eve . After a ton of research , dozens of prototypes, and a slew of tests we’ve finally come to something that we think is the beginning of Eve. It’s still in its infancy with lots missing and assuredly more than a few bugs, but it’s reached a point…
What I cannot create, I do not understand. – Richard Feynman I do a lot of video chat for work. If it’s not a one on one, it’s pair programming. If it’s not pair programming…
Posted on Monday 10 Oct 2022. 1,417 words, 11 links. By Matt Webb.
The first beta of Sublime Text 3 is now available to download for registered users. Some feature highlights are below, followed by our new pricing and upgrade policies, and system compatibility for Sublime Text 3.
GPT-5.2-Codex is OpenAI’s most advanced coding model, offering long-horizon reasoning, large-scale code transformations, and enhanced cybersecurity capabilities.
An agent harness is a piece of software that provides an environment for an AI model to operate within.
Every week, a new AI model climbs to the top of a benchmark leaderboard. Companies cite these numbers in press releases. Investors use them to justify valuations. Engineers use them to pick which model to deploy. The implicit promise is simple: a higher score means a more capable system.
An overview of a class of data structures I didn't know about!
Which is good! Boring = success
Open Source, Web Development, and more
Your phone's ability to identify any song it listens to is pure technological magic. In this article, I'll show you how one of the most popular apps, Shazam , does it. The founders of Shazam released a paper in 2003 documenting how it works, and I have been working on an implementation of that paper, abracadabra .
Why is everyone in such a rush? Walk into any bookstore, and you'll see how to Teach Yourself Java in 24 Hours alongside endless variations offering to teach C, SQL, Ruby, Algorithms, and so on in a few days or hours. The Amazon advanced search for [ title: teach, yourself, hours, since: 2000 and found 512 such books…
Access to this page requires authorization. You can try signing in or changing directories .
The other month I finally ran an experiment we had been postponing for over a year at .txt.
[Note: there have been several developments in this space since thisarticle was published. See A Tail Calling Interpreter For Python (And Other Updates) for...
A gallery that collects architecture figures from The Big LLM Architecture Comparison and related articles, with fact sheets and links back to the original sections.
Tell me you don’t understand software without literally using those words!!!
Lessons learned from 15 years of writing SumatraPDF, a great open-source PDF, eBook, and comic book reader for Windows
On March 8, out of an abundance of caution, we logged all users out of GitHub.com. In this post we share technical details of the vulnerability and steps we're taking to ensure it doesn't happen again.
Livebook is a web application for writing interactive and collaborative code notebooks
iTerm2 is a replacement for Terminal and the successor to iTerm
rqlite is a lightweight, open-source, distributed relational database written in Go, which uses SQLite as its storage engine. Recently I introduced a high-performance write-path into rqlite and, to my great surprise, it exposed a bug in SQLite. The SQLite team quickly addressed the issue but let's take a look at the…