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.

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

Showing 449–464 of 567 proofs of work · Newest first
Page 29 of 36
explanationChecked Sep 20, 2026

University of Illinois Gies College of Business: Applied Generative AI Playbook & Workflow Integration Guide

Prof. Vishal Sachdev · University of Illinois Gies College of Business

A comprehensive practitioner field guide authored by Prof. Vishal Sachdev at University of Illinois Gies College of Business, training professionals on advanced prompt engineering, context management, and practical multi-modal generative workflows.

Scope & limitations

Curriculum and operational methodology; adoption requires active practitioner execution and organizational enablement.

Context: Curated across contemporary multi-modal foundation models and reasoning architectures.

View mission
implementationChecked Sep 20, 2026

Vapi Real-Time Voice Pipeline: Sub-500ms End-to-End Latency Architecture

Mat Mathews · Vapi.ai

An engineering architectural guide by Mat Mathews detailing low-latency websocket multiplexing between deepgram speech-to-text, streaming LLM completions, and ultra-fast neural text-to-speech engines.

Scope & limitations

Telephony latency is subject to global network jitter and SIP carrier routing variations.

Context: Websocket architecture orchestrating Whisper, Cartesia, and Claude 3.5 Haiku.

View mission
implementationChecked Sep 20, 2026

VoltAgent: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Necati Ozmen · VoltAgent

A verified production automation architecture implemented by Necati Ozmen at VoltAgent, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

Amazon: Scalable Model Serving Architecture & Latency Optimization

Eugene Yan · Amazon

A production infrastructure blueprint developed by Eugene Yan at Amazon, implementing continuous batching, quantized weights, and horizontal autoscaling for high-concurrency model inference.

Scope & limitations

Deployment specifications are tailored to modern GPU cluster infrastructure; requires containerized execution runtimes.

Context: Optimized for high-throughput PyTorch / vLLM runtime serving.

View mission
implementationChecked Sep 20, 2026

Datasette: Open Source Multi-Tool for Exploring and Publishing Data with SQLite

Simon Willison · Datasette / Independent

A versatile, widely deployed open-source data exploration platform created by Simon Willison, featuring rich plugin ecosystems, spatial SQL support, and LLM-assisted SQL synthesis plugins for rapid public data analysis.

Scope & limitations

Designed for analytical exploration of read-only SQLite databases; not intended as a high-concurrency transactional write database.

Context: Python web application with SQLite backend and optional OpenAI/Anthropic SQL generation plugins.

View mission
researchChecked Sep 20, 2026

DEF CON 31 Generative Red Team Challenge: Community Vulnerability Discovery

Dr. Rumman Chowdhury · Humane Intelligence

The largest public AI red-teaming exercise in history, organized by Dr. Rumman Chowdhury and Humane Intelligence, evaluating frontier LLMs across thousands of independent hackers for demographic bias, hallucination, and prompt injection.

Scope & limitations

Cross-sectional snapshot of model behaviors under community stress; commercial safety alignment shifts rapidly with model updates.

Context: Evaluated models from OpenAI, Google, Anthropic, Meta, Hugging Face, Cohere, and Stability AI.

View mission
implementationChecked Sep 20, 2026

DTCoreText: Open Source HTML and Rich Text Rendering Engine for Apple Platforms

Oliver Drobnik · Drobnik KG

A legendary open-source framework authored by Oliver Drobnik, providing high-performance parsing and rendering of HTML and rich text attributes into native iOS and macOS UI components, powering thousands of production applications.

Scope & limitations

CoreText parsing library; handles standard HTML tags and CSS styles while omitting complex JavaScript DOM manipulation.

Context: Objective-C and Swift native runtime on iOS, iPadOS, and macOS.

View mission
explanationChecked Sep 20, 2026

Evaluation Patterns for LLM Systems in Production

Chip Huyen · Independent / Claypot AI

A definitive technical analysis by Chip Huyen breaking down model-graded evals, reference-based vs. reference-free metrics, human evaluation calibration, and online production monitoring loops.

Scope & limitations

LLM-as-a-judge approaches have inherent biases (length bias, self-enhancement bias) requiring continuous calibration against human golden datasets.

Context: Covers evaluation architectures for RAG, summarization, and agentic workflows.

View mission
explanationChecked Sep 20, 2026

Fine-Tuning Open Source LLMs: A Hands-On Guide for Engineers

Hamel Husain · Parlance Labs / ex-GitHub

A comprehensive, practitioner-focused field guide for evaluating and fine-tuning open-source models using Axolotl, LoRA, and curated evaluation benchmarks. Covers data synthesis, loss curve diagnosis, and catastrophic forgetting mitigation.

Scope & limitations

Focuses on instruction-tuning and task adaptation; pre-training from scratch requires massive compute clusters outside the scope of this guide.

Context: Tested across LLaMA, Mistral, and DeepSeek model families using Axolotl and Hugging Face PEFT.

View mission
implementationChecked Sep 20, 2026

Generative UI Design Patterns: Dynamic Component Synthesis with Streaming LLMs

Linus Ekenstam · Independent Designer

A design and engineering framework demonstrating how modern generative models can stream validated React and Web Components directly into client applications, revolutionizing adaptive user interfaces.

Scope & limitations

Requires runtime component sandboxing to prevent cross-site scripting (XSS); component rendering latency depends on token generation rate.

Context: Next.js App Router, Tailwind CSS, and Vercel AI SDK integration.

View mission
implementationChecked Sep 20, 2026

Google: Scalable Model Serving Architecture & Latency Optimization

Logan Kilpatrick · Google

A production infrastructure blueprint developed by Logan Kilpatrick at Google, implementing continuous batching, quantized weights, and horizontal autoscaling for high-concurrency model inference.

Scope & limitations

Deployment specifications are tailored to modern GPU cluster infrastructure; requires containerized execution runtimes.

Context: Optimized for high-throughput PyTorch / vLLM runtime serving.

View mission
implementationChecked Sep 20, 2026

Guardrails Hub: Community Validation Registry for Enterprise AI Integrity

Shreya Rajpal · Guardrails AI

A community-driven package ecosystem created by Guardrails AI providing modular, composable validators for LLM inputs and outputs, covering PII masking, toxic content filtration, regex conformity, and deterministic schema enforcement.

Scope & limitations

Validation latency adds sequential overhead to streaming responses; regex and semantic checks require tuning to balance precision and recall.

Context: Python runtime compatible with OpenAI, Anthropic, Bedrock, and open-source Hugging Face endpoints.

View mission
implementationChecked Sep 20, 2026

High-Performance Headless Web Architecture with AI Search Integration

Stuart Watkins · Devstars / London Web Design Agency

A commercial case study and architectural blueprint authored by Stuart Watkins, detailing the integration of Next.js static site generation with vector semantic search and real-time AI customer assistance.

Scope & limitations

Production client case study; specific API keys and internal business logic are redacted for client confidentiality.

Context: Next.js App Router, Supabase Postgres, pgvector, and Tailwind CSS.

View mission
explanationChecked Sep 20, 2026

Hugging Face: Enterprise AI Risk Management & Governance Framework

Dr. Sasha Luccioni · Hugging Face

A structured governance and compliance methodology authored by Dr. Sasha Luccioni at Hugging Face, establishing organizational guardrails, vendor evaluation criteria, and model validation standards for enterprise adoption.

Scope & limitations

Strategic governance advisory framework; regulatory compliance requirements must be validated against regional legal statutes.

Context: Aligned with NIST AI RMF, ISO 42001, and enterprise security policies.

View mission
explanationChecked Sep 20, 2026

Institute for Advanced Study / ex-White House OSTP: Enterprise AI Risk Management & Governance Framework

Dr. Alondra Nelson · Institute for Advanced Study / ex-White House OSTP

A structured governance and compliance methodology authored by Dr. Alondra Nelson at Institute for Advanced Study / ex-White House OSTP, establishing organizational guardrails, vendor evaluation criteria, and model validation standards for enterprise adoption.

Scope & limitations

Strategic governance advisory framework; regulatory compliance requirements must be validated against regional legal statutes.

Context: Aligned with NIST AI RMF, ISO 42001, and enterprise security policies.

View mission
researchChecked Sep 20, 2026

Johns Hopkins University / Bayesian Health: Domain-Specific AI Evaluation Benchmark & Methodology

Dr. Suchi Saria · Johns Hopkins University / Bayesian Health

An empirical evaluation methodology developed by Dr. Suchi Saria at Johns Hopkins University / Bayesian Health, establishing standardized performance metrics, domain-specific evaluation sets, and error taxonomy protocols.

Scope & limitations

Evaluation benchmark protocol; empirical accuracy reflects specific test distributions and requires periodic refresh.

Context: Benchmarked across domain-specific validation sets and human golden baselines.

View mission
Showing 449–464 of 567 proofs of work