EsoLang-Bench: Evaluating Genuine Reasoning in LLMs via Esoteric Languages
Current benchmarks for large language model (LLM) code generation primarily evaluate mainstream languages like Python, where models benefit from massive pretraining corpora. This leads to inflated accuracy scores that may reflect data memorization rather than genuine reasoning ability. We introduce EsoLang-Bench, a benchmark of 80 programming problems across five esoteric languages (Brainfuck, Befunge-98, Whitespace, Unlambda, […]
Cockpit is a web-based graphical interface for servers
A sysadmin login session in a web browser cockpit-project.org Cockpit is an interactive server admin interface. It is easy to use and very lightweight. Cockpit interacts directly with the operating system from a real Linux session in a browser. Using Cockpit You can install Cockpit on many Linux operating systems including Debian, Fedora and RHEL. […]
Waymo Safety Impact
A crashed vehicle rate or vehicle-level rate is computed by counting the number of vehicles involved in crashes at a certain outcome level and dividing by the population-level VMT. For the Waymo crashes, the crashed vehicle rate is computed as the number of Waymo vehicles in crashes with a given outcome level divided by the […]
Tesla: Failure of the FSD’s degradation detection system [pdf]
Download PDF
My first patch to the Linux kernel
Mar 19, 2026 How a sign-extension bug in C made me pull my hair out for days but became my first patch to the Linux kernel! Intro A while ago, I started dipping my toe into virtualization. It’s a topic that many people have heard of or are using on a daily basis but a […]
From Oscilloscope to Wireshark: A UDP Story (2022)
From Oscilloscope to Wireshark: A UDP Story UDP is a transport-level protocol for sending messages through an IP network. It sits at level 4 in the OSI model: 7 Application 6 Presentation 5 Session 4 Transport 3 Network 2 Data link 1 Physical Like many of you, I’ve got hardware on my desk that’s sending […]
Gerd Faltings, who proved the Mordell conjecture, wins the Abel Prize
March 19, 2026 3 min read Add Us On GoogleAdd SciAm The Mordell conjecture—now known as Faltings’s theorem—concerns the number of special points on a curve By Joseph Howlett edited by Clara Moskowitz At age 71, German mathematician Gerd Faltings was awarded the Abel Prize today. Peter Badge/Typos1/The Abel Prize This year’s Abel Prize, an […]
NanoGPT Slowrun: 10x Data Efficiency with Infinite Compute
We’ve achieved 10x data efficiency with NanoGPT Slowrun within a few weeks. An ensemble of 1.8B parameter models (18B total params) trained on 100M tokens matches what would normally require 1B tokens with a standard LM baseline. Data efficiency matters because compute grows much faster than data . Since our current scaling laws require proportional […]
The quadratic problem nobody fixed
search a document for a pattern and it takes a second. search one a hundred times larger and it doesn’t take a hundred seconds – it can take almost three hours. every regex engine, in every language, has had this problem since the 1970s, and nobody fixed it. (this is a follow-up to RE#: how […]
Noq: n0’s new QUIC implementation in Rust
Today we’re delighted to announce noq (”number 0 QUIC”), our own general purpose QUIC implementation with multipath and NAT traversal support. It is the transport layer that has been powering iroh since v0.96, though is in no way limited to iroh’s usecase. If you’ve been following iroh’s development, you may have read why we forked […]