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 49–64 of 177 proofs of work · Kind: explanation · Newest first
Page 4 of 12
explanationChecked Sep 22, 2026

AI Product Management Frameworks and Evaluation Rubrics

Aakash Gupta · Product Growth / Independent Advisory

Formulated the foundational operational frameworks for AI PMs, detailing how to manage stochastic failure states, set confidence thresholds, and instrument telemetry for generative features.

Scope & limitations

Frameworks must be adapted when transitioning from deterministic classification to unstructured creative generation.

Context: Human-in-the-loop UX, confidence score routing, telemetry instrumentations.

View mission
explanationChecked Sep 22, 2026

AI4Diversity: Global Frameworks for Ethical and Inclusive AI Models

Steve Nouri · AI4Diversity / Generative AI

Led international community initiatives uniting 100,000+ practitioners to establish open audit standards for algorithmic fairness, demographic parity, and cultural representation in LLMs.

Scope & limitations

Cultural fairness benchmarks vary widely across international jurisdictions and local idioms.

Context: Algorithmic bias detection, fairness metrics, multilingual evaluation datasets.

View mission
explanationChecked Sep 22, 2026

An ex-OpenAI researcher just deleted language from the LLM...

Jeff Delaney · Fireship.io

Analyzed the shift from manual coding to conversational, prompt-guided software engineering using Cursor, Claude 3.5 Sonnet, and Copilot, demonstrating rapid full-stack application synthesis.

Scope & limitations

AI-first vibe coding requires developer intuition to catch security vulnerabilities and silent edge-case logic failures.

Context: Cursor AI, Claude 3.5 Sonnet, Next.js, Supabase, Tailwind CSS.

View mission
explanationChecked Sep 22, 2026

Astra Head-to-Head with Fable 5.1: Putting OpenAI's True AGI Claims to the Test

Ed Donner · Ed Donner AI / Independent Advisory

Delivered comprehensive architectural walkthrough detailing enterprise latency SLAs, token economics, fallback routing, and validation layers for financial services.

Scope & limitations

Financial services data governance requires rigorous PII scrubbing before sending payloads to cloud LLMs.

Context: GPT-4o, Claude 3.5 Sonnet, AWS Bedrock, enterprise VPC security.

View mission
explanationChecked Sep 22, 2026

Autonomous Procurement and Digital Supply Chain AI Transformation

Dr. Marcell Vollmer · Prospance Inc. / Former SAP CDO

Published research detailing how process mining and generative AI automate invoice processing, contract compliance, supplier negotiations, and fraud detection in Fortune 500 supply chains.

Scope & limitations

Legacy ERP database schemas require custom middleware translation to support LLM structured ingestion.

Context: ERP integrations (SAP, Oracle), Celonis process mining, LLM contract extraction.

View mission
explanationChecked Sep 22, 2026

Autonomous Software Engineering and Frontier Safety Evaluation Metrics

Michael Spencer · AI Explained

Formulated comparative methodology for auditing agentic code generation harnesses against real-world GitHub issues, isolating scaffolding efficacy from raw model intelligence.

Scope & limitations

Unit test pass rates on narrow issue fixes do not evaluate entire codebase architectural coherence.

Context: SWE-bench test harness, Docker execution sandboxes, Claude 3.5 Sonnet.

View mission
explanationChecked Sep 22, 2026

Build Anything with Jev, Here’s How

David Ondrej · Prompt Engineering / Ondrej AI

Constructed and benchmarked cooperative multi-agent architectures that divide research, code synthesis, testing, and documentation across specialized role-based models.

Scope & limitations

Inter-agent communication drift can cause repetitive conversation loops without strict supervisor termination conditions.

Context: AutoGen, CrewAI, GPT-4o, Claude 3.5 Sonnet, local LLaMA-3 models.

View mission
explanationChecked Sep 22, 2026

Building and Scaling an Applied AI Consulting Agency

Dave Ebbelaar · Datalumina / Independent AI Agency

Trained over 5,000 software engineers and consultants on scoping, pricing, and delivering real enterprise AI projects with deterministic acceptance criteria and verifiable ROI.

Scope & limitations

Client proprietary data compliance (GDPR/HIPAA) limits usage of non-EU cloud model APIs.

Context: Enterprise client delivery frameworks, SLA definition for stochastic models.

View mission
explanationChecked Sep 22, 2026

ChatGPT and Healthcare: Clinical Applications and Diagnostic Augmentation

Dr. Harvey Castro · Healthcare AI Advisory

Authored the first medical reference manual for physicians examining generative AI utility in clinical note generation, patient triage, and medical education.

Scope & limitations

Generative LLMs must never replace primary clinical diagnostic reasoning without board-certified physician oversight.

Context: Clinical documentation, HIPAA data privacy, emergency medicine triage.

View mission
explanationChecked Sep 22, 2026

Collaborative Prompting: Conversational AI Workflows for Business Teams

Conor Grennan · NYU Stern / Generative AI

Formulated the 'collaborative prompting' methodology taught across NYU Stern executive programs, replacing static prompt templates with iterative dialogic steering.

Scope & limitations

Iterative prompting relies on user critical thinking to recognize and steer model assumptions.

Context: GPT-4o, Claude 3.5 Sonnet, iterative conversational prompting, business communication.

View mission
explanationChecked Sep 22, 2026

Data Science as a Service | Kumo AI Full Walkthrough

James Briggs · James Briggs AI / Vector Search Advisory

Authored technical video investigation comparing dense vector embeddings versus reciprocal rank fusion (RRF) with BM25 sparse vectors, demonstrating 28% improvement in Mean Reciprocal Rank (MRR).

Scope & limitations

Two-stage retrieval pipelines introduce 100-250ms of additional network latency for the reranking stage.

Context: Pinecone, Cohere Rerank, BM25, text-embedding-3-large, LangChain.

View mission
explanationChecked Sep 22, 2026

Decision Intelligence: The Unifying Framework for AI Strategy

Cassie Kozyrkov · Data Scientific

Formulated the foundational principles of Decision Intelligence, integrating managerial science, behavioral economics, and machine learning to improve executive AI decision-making.

Scope & limitations

Framework requires quantitative literacy across executive leadership teams.

Context: Decision intelligence, statistical hypothesis testing, AI error budgeting.

View mission
explanationChecked Sep 22, 2026

Deepfakes and the Synthetic Media Era: Authenticity and Provenance Standards

Nina Schick · Tamang Ventures

Authored the foundational commercial book on generative synthetic media, establishing the necessity of cryptographic watermarking standards like C2PA for digital media verification.

Scope & limitations

Cryptographic metadata can be stripped during social media platform transcoding and compression.

Context: C2PA cryptographic provenance, deepfake detection, synthetic voice and video generation.

View mission
explanationChecked Sep 22, 2026

Deploying Private and Air-Gapped Foundation Models in Regulated Industries

Pascal Bornet · Pascal Bornet / IRREPLACEABLE

Authored technical deployment playbooks for hosting open-weights models (Mistral, LLaMA) on internal private clouds with zero telemetry data exfiltration.

Scope & limitations

Self-hosted hardware infrastructure demands substantial upfront CAPEX compared to serverless cloud APIs.

Context: On-premise vLLM, confidential computing, isolated network topologies.

View mission
explanationChecked Sep 22, 2026

Did Elon catch up? (Grok 4.7 is here)

Matthew Berman · Forward Future

Published hands-on architectural walkthrough testing quantization trade-offs, GPU VRAM caching, and local Ollama server orchestration across Llama-3, DeepSeek, and Mistral models.

Scope & limitations

Local inference throughput is bounded by available unified memory bandwidth on consumer workstations.

Context: Local quantized GGUF weights, Ollama, vLLM, LM Studio, consumer GPU hardware.

View mission
Showing 49–64 of 177 proofs of work