PUBLISHED AI RESEARCH AND PROJECTS

AI research and projects

The research, projects, and explanations behind the people. Read the source, inspect verified code and models, and find a collaborator.

Clear all filters

A source check confirms that a source supports the summary. It is not an independent replication or endorsement. Our methodology ↗

Showing 129–144 of 241 proofs of work · Kind: implementation · Newest first
Page 9 of 16
implementationChecked Sep 22, 2026

Voice-First Multimodal Agent Harnesses and Vibe Coding Workflows

Mckay Wrigley · Takeoff / Chatbot UI

Developed real-time voice agent prototypes combining WebSocket audio streaming, low-latency function calling, and Cursor-driven rapid software development workflows.

Scope & limitations

WebSocket audio streams are sensitive to network packet jitter and browser audio permissions.

Context: OpenAI Realtime API, Cursor AI code generation, ElevenLabs streaming audio.

View mission
implementationChecked Sep 22, 2026

Web Cafe AI Client Knowledge Base & Agent Templates

Corbin Brown · Web Cafe AI

Engineered reusable client delivery frameworks for syncing Notion, Google Drive, and Zendesk data into secure embedding indexes with role-based access control.

Scope & limitations

Incremental document sync requires webhook event listeners to capture upstream edits in real time.

Context: LangChain, ChromaDB, FastAPI, Next.js, Tailwind CSS.

View mission
implementationChecked Sep 22, 2026

Writing An Interpreter and Compiler In Go

Thorsten Ball · Independent Author & Systems Engineer

Authored two landmark engineering books used by university curricula and tens of thousands of systems engineers worldwide to learn lexing, parsing, AST generation, and bytecode virtual machines.

Scope & limitations

Focuses on language implementation theory rather than modern JIT compiler optimizations.

Context: Go, lexer/parser construction, tree-walking interpreters, bytecode compilers.

View mission
implementationChecked Sep 21, 2026

AlphaFold 2: Computational Structural Biology Prediction Engine Across 200M+ Proteins

Dr. John Jumper · Google DeepMind

First author and technical architect of the open-source AlphaFold 2 computational system, predicting 3D coordinates of all cataloged proteins in the UniProt database with atomic precision.

Scope & limitations

Computational requirements for long sequence complexes (>2000 residues) require high-memory GPUs (A100/H100).

Context: JAX/Haiku, Multiple Sequence Alignment (MSA) representations, structural recycling iterations.

View mission
implementationChecked Sep 21, 2026

Cursor Speculative Code Editing & Shadow Workspace Architecture

Aman Sanger · Cursor / Anysphere

Architected Cursor's instant-apply and speculative editing engine, which runs isolated shadow syntax trees to predict multi-token keystrokes and merge large diffs into production codebases with zero visual latency.

Scope & limitations

Requires real-time AST parsing and language server protocol (LSP) indexing to ensure semantic validity of speculative edits.

Context: Custom fine-tuned small speculative draft models paired with frontier reasoning models (Claude 3.5 Sonnet, GPT-4o).

View mission
implementationChecked Sep 21, 2026

FLUX.1: 12B Parameter Rectified Flow Transformer for High-Fidelity Image Generation

Dr. Robin Rombach · Black Forest Labs

Architected FLUX.1, an open-weights 12B parameter multimodal diffusion transformer utilizing rectified flow matching, achieving unmatched prompt adherence, typography generation, and photographic realism.

Scope & limitations

12B model footprint requires 24GB+ VRAM or 8-bit/4-bit quantization (NF4) for local inference on consumer hardware.

Context: 12B parameter multimodal Diffusion Transformer (MMDiT), rectified flow matching, rotary positional embeddings.

View mission
implementationChecked Sep 21, 2026

llama.cpp: High-Performance C/C++ Foundation Model Inference Engine

Georgi Gerganov · ggml.ai

Engineered a zero-dependency C/C++ LLM inference framework implementing 2-bit through 8-bit integer quantization (GGUF), ARM NEON, Apple Silicon Metal, CUDA, and AVX2 vector intrinsics, powering the modern local AI ecosystem.

Scope & limitations

Extreme low-bit quantizations (2-bit/3-bit) exhibit perplexity degradation on complex symbolic reasoning tasks.

Context: GGUF quantization format, Llama 2/3, Mistral, Qwen, DeepSeek; pure C/C++ runtime.

View mission
implementationChecked Sep 21, 2026

Multi-File Codebase Indexing & Semantic Agentic Refactoring

Aman Sanger · Cursor / Anysphere

Engineered local embedding and symbol graph pipelines capable of indexing hundred-thousand-line monorepos into contextual embeddings, enabling multi-step agentic software modifications.

Scope & limitations

Context budgets require strict retrieval pruning in repositories with dense circular dependencies.

Context: Custom tree-sitter chunking, semantic vector index, agentic terminal command execution loop.

View mission
implementationChecked Sep 21, 2026

The Mojo Programming Language for AI Hardware Kernel Development

Dr. Chris Lattner · Modular

Designed and built Mojo, a high-performance language that combines Python syntax and developer ergonomics with systems programming primitives, SIMD vectorization, and hardware-accelerated memory ownership.

Scope & limitations

Ecosystem packages and third-party library bindings are actively expanding relative to decades-old C++/CUDA tooling.

Context: Modular MAX Engine, Mojo compiler, heterogenous CPU/GPU execution pipelines.

View mission
implementationChecked Sep 21, 2026

Unsloth: Fast and Memory-Efficient Open-Source LLM Fine-Tuning

Daniel Han · Unsloth AI

Created an open-source library that rewrites PyTorch forward and backward passes into handwritten Triton kernels, supporting LoRA, QLoRA, and full fine-tuning with 0% accuracy loss while preventing out-of-memory errors.

Scope & limitations

Heavily optimized for NVIDIA Ampere, Ada Lovelace, and Hopper architectures; AMD ROCm support is emerging.

Context: Llama 3.1/3.2, Mistral NeMo, DeepSeek-R1-Distill, Gemma 2; 4-bit bitsandbytes and 16-bit mixed precision.

View mission
implementationChecked Sep 21, 2026

vLLM: High-Throughput and Memory-Efficient LLM Serving Engine

Woosuk Kwon · vLLM / UC Berkeley

Engineered and open-sourced vLLM, an enterprise serving system providing continuous batching, chunked prefill, speculative decoding, and tensor parallelism, serving billions of production inference tokens daily worldwide.

Scope & limitations

Requires dedicated GPU clusters and NVLink interconnects for multi-node tensor-parallel deployments.

Context: CUDA/ROCm kernels, Triton backends, Ray distributed orchestration, vLLM OpenAI-compatible server.

View mission
implementationChecked Sep 21, 2026

whisper.cpp: High-Performance Automatic Speech Recognition in Pure C/C++

Georgi Gerganov · ggml.ai

Developed a pure C/C++ port of OpenAI Whisper speech recognition with zero external dependencies, streaming audio support, WebAssembly compilation, and hardware acceleration on Apple Silicon and mobile devices.

Scope & limitations

Real-time streaming requires audio buffering and speech activity detection (VAD) to prevent hallucinated audio loops.

Context: OpenAI Whisper tiny/base/small/medium/large models, 16-bit float and 4-bit/5-bit/8-bit integer quantization.

View mission
implementationChecked Sep 20, 2026

AutoResearch: Autonomous AI Research Agent Conducting Iterative ML Experiments

Andrej Karpathy · Eureka Labs / ex-Tesla, OpenAI

An autonomous multi-step research agent framework designed to conduct end-to-end machine learning experimentation without human intervention. The agent autonomously formulates algorithmic hypotheses, modifies PyTorch model architectures via AST rewriting, schedules multi-GPU training jobs, parses validation loss curves, and generates structured empirical research reports and pull requests.

Scope & limitations

Requires sandboxed execution environments to prevent arbitrary code execution risks during dynamic model definition; experiments can diverge if loss curves suffer from exploding gradients without bounded learning rate search spaces.

Context: PyTorch 2.4, LLM function calling, Automated Evaluation Loop, Python AST manipulation, TensorBoard metric parsing.

View mission
implementationChecked Sep 20, 2026

llm.c: Large Language Model Training in Pure C/CUDA Without Dependencies

Andrej Karpathy · Eureka Labs / ex-Tesla, OpenAI

A zero-dependency, pure C and CUDA implementation of GPT-2 and modern transformer pre-training. Eliminates the 245MB+ PyTorch/Python runtime overhead by directly implementing forward passes, backward passes, AdamW optimizers, and fused CUDA kernels in a single clean compilation unit, achieving near-parity with PyTorch cuDNN speed.

Scope & limitations

Lower level of architectural expressiveness compared to dynamic Python autograd graphs; adding novel attention variations requires manual mathematical derivation and custom CUDA kernel writing.

Context: Pure C99, CUDA 12, FP32 and BF16 mixed-precision kernels, fused attention, multi-GPU MPI execution.

View mission
implementationChecked Sep 20, 2026

Automated Code Review and PR Triage AI Assistant

Michael Ballard · Slashdev

Built a GitHub Action and webhook bot that analyzes incoming pull requests, identifies security vulnerabilities and formatting anti-patterns, and generates unit test coverage proposals automatically.

Scope & limitations

Large pull requests exceeding 2,000 lines require chunking across logical Git commits to fit within prompt context ceilings.

Context: Claude 3.5 Sonnet, GitHub Octokit API, AST tree-sitter parsers.

View mission
implementationChecked Sep 20, 2026

Automated Content Repurposing Engine for Long-Form Media

Paul Macko · Deplatformable / Macko Media

Built an end-to-end automated workflow that ingests audio podcasts, generates precise Whisper transcripts, identifies viral hooks using LLM evaluation, and renders styled short-form video clips automatically.

Scope & limitations

Multi-speaker audio with heavy background music can lead to transcript misalignment without voice separation preprocessing.

Context: Whisper API, Claude 3.5 Sonnet, FFmpeg command automation, Python script runner.

View mission
Showing 129–144 of 241 proofs of work