Happy Zelda’s 40th first LLM running on N64 hardware (4MB RAM, 93MHz)
A nano-GPT language model running entirely on a 93 MHz VR4300 MIPS CPU. No cloud. No cheating. Real 1996 silicon, real neural inference. What is This? Legend of Elya is an original N64 homebrew game featuring Sophia Elya — a character-level LLM (nano-GPT) running live on-cart on the Nintendo 64’s VR4300 CPU. Sophia generates responses […]
Password managers less secure than promised
People who regularly use online services have between 100 and 200 passwords. Very few can remember every single one. Password managers are therefore extremely helpful, allowing users to access all their passwords with just a single master password. Most password managers are cloud based. A major advantage this offers users is the ability to access […]
Why is Claude an Electron App?
If code is free, why aren’t all apps native? The state of coding agents can be summed up by this fact Claude spent $20k on an agent swarm implementing (kinda) a C-compiler in Rust, but desktop Claude is an Electron app. If you’re unfamiliar, Electron is a coding framework for building desktop applications using web […]
Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU
High-efficiency C++/CUDA LLM inference engine. Runs Llama 70B on a single RTX 3090 (24GB VRAM) by streaming model layers through GPU memory via PCIe, with optional NVMe direct I/O that bypasses the CPU entirely. Key Results Model Mode Decode VRAM Notes Llama 3.1 8B Q8_0 Resident 48.9 tok/s 10.0 GB All layers in VRAM Llama […]
EDuke32 – Duke Nukem 3D (Open-Source)
Per-pixel dynamic lighting and realtime shadows… groovy! Polymer renderer requires a bad-ass video card. More Polymer greatness. Hollywood Holocaust with classic textures Come get some! EDuke32 is an awesome, free homebrew game engine and source port of the classic PC first person shooter Duke Nukem 3D— Duke3D for short—to Windows, Linux, macOS, FreeBSD, several handhelds, […]
Inputlag.science – Repository of knowledge about input lag in gaming
Home |inputlag.science inputlag.science Welcome Hello traveler, welcome to the repository of knowledge about input lag in gaming. The input lag in a gaming system, or any interactive system, is the latency between the user input and a reaction on the screen. Input lag is an issue that has crept in the industry, little by little, […]
Parse, Don’t Validate and Type-Driven Design in Rust
Reading time: 17 min read Table of Contents 1.1 Dividing by zero 1.2 Examples in the wild 1.3 Maxims of Type Driven Design 1.4 What can we do? 1.5 Conclusion Photo by the Tingley Injury Law Firm. In the Rust Programming Language Community Server, there’s tag named -parse-dont-validate which links to an article about the […]
How Taalas ”prints” LLM onto a chip?
or how to generate 17000 tokens per second? February 22, 2026 · 4 min read A startup called Taalas, recently released an ASIC chip running Llama 3.1 8B (3/6 bit quant) at an inference rate of 17,000 tokens per seconds. That’s like writing around 30 A4 sized pages in one second. They claim it’s 10x […]
Cloudflare outage on February 20, 2026
On February 20, 2026, at 17:48 UTC, Cloudflare experienced a service outage when a subset of customers who use Cloudflare’s Bring Your Own IP (BYOIP) service saw their routes to the Internet withdrawn via Border Gateway Protocol (BGP). The issue was not caused, directly or indirectly, by a cyberattack or malicious activity of any kind. […]
Canvas_ity: A tiny, single-header -like 2D rasterizer for C++
Example const context = document.getElementById( ”example” ).getContext( ”2d” ); // Build a star path. context.moveTo( 128.0, 28.0 ); context.lineTo( 157.0, 87.0 ); context.lineTo( 223.0, 97.0 ); context.lineTo( 175.0, 143.0 ); context.lineTo( 186.0, 208.0 ); context.lineTo( 128.0, 178.0 ); context.lineTo( 69.0, 208.0 ); context.lineTo( 80.0, 143.0 ); context.lineTo( 32.0, 97.0 ); context.lineTo( 98.0, 87.0 ); context.closePath(); […]