Rasmus Lindahl

IntuitiveEngine. A simple 3D engine made only with 2D drawLine functions.

human-level-agi-definition.

i3_meta_workspaces. This code enables multiple meta workspaces within your i3 window manager. It is very useful when working in multiple projects.

BenchmarkAggregator. Comprehensive LLM evaluation framework: GPQA Diamond to Chatbot Arena. Tests all major models equally, easily extensible.

PullRequestBenchmark. Evaluating LLMs performance in PR reviews as an indicator for their capability in creating PRs.

WikiGenGPT. WikiGenGPT creates fictional Wikipedia articles using GPT-4 API for imaginative exploration.

SnippetDepot. This git contains the code for a proof of concept extension to VS Code that enables real-time retrieving of code snippets from an online repository.

huggingface-paper-explorer. HuggingFace Paper Explorer: Extended time range for top AI research papers.

Simple-TCP-Communication-SSLStream. A simple TCP server and client both wrapped with a SLLStream with a self-signed certificate. Written in C#.

model-clash. Autonomous AI tournament with self-generated challenges for competitive language model evaluation.

The-Long-Division-Benchmark. Evaluating LLMs' context handling and text generation using long division.

LongScope. LongScope is a benchmark for assessing large language models' ability to handle fragmented knowledge in extended textual contexts.

FloatView. Auto-positioning video browser that finds and fills unused screen space

VoiceMouse. Android app controlling PC mouse via voice pitch and volume.

The-Long-Multiplication-Benchmark. Evaluating LLMs' context handling and text generation using long multiplication.

life-happiness-index. Calculates happiness likelihood from 33 objective life factors using statistics.

the-button-thought-experiment.

dice-bench. TypeScript

h-matched-tracker. TypeScript