Tokenless

Tokenless

Make Your AI Agents Predictable With Graph Engineering - Zachary Blumenfeld, Neo4j

Interactive discovery

Explore the topic map

Follow the connections between themes, people, and ideas across the Tokenless archive in an interactive topic modeling map.

Open the map Browse posts

Machine Learning

View All
Judge a Transaction by the Company It Keeps — Somya Rai & MD Sharique, EXL

Judge a Transaction by the Company It Keeps — Somya Rai & MD Sharique, EXL

EXL developed an advanced fraud detection system that augments XGBoost with Graph Neural Network (GNN) embeddings. Traditional tabular models struggle to capture fraud signals residing in transaction neighborhoods. The system's innovative design includes meticulous sampling strategies, disjoint monthly graph construction for leakage control, and a GraphSAGE architecture that aggregates mean, max, and standard deviation of neighbor features to detect subtle fraud patterns. Emphasizing explainability for regulatory compliance and analyst trust, it also features a highly optimized serving architecture achieving 3ms P99 latency, pivoting to edge prediction to reduce cache footprint from 60GB to 2-3GB. This led to a 27-33% relative lift in true positive rates and a projected $65 million incremental fraud capture.

From 15% to 90% GPU Utilization: Fix the Data Pipeline, Not the Model

From 15% to 90% GPU Utilization: Fix the Data Pipeline, Not the Model

Tarun Sunkaraneni from Amazon AGI shows how a multimodal SFT pipeline that spent about 85% of its time waiting on data was brought to roughly 90% GPU utilization. He walks through concurrency with asyncio and Ray actors, prefetching, zero-copy transfer via Ray's object store, and a network-card bottleneck that appears only at scale, and argues that the hardest part of training throughput is often keeping GPUs fed rather than optimizing the model.

Small Models, Big Results: Training a Finance Agent for Under $500 — Charles Dickens, Snorkel AI

Small Models, Big Results: Training a Finance Agent for Under $500 — Charles Dickens, Snorkel AI

Snorkel AI and UC Berkeley's Sky Computing Lab show that a 4B Qwen3 model, trained with reinforcement learning for under $500 using the rLLM framework, beats its 235B sibling on expert-validated financial question answering built from SEC 10-K filings. The talk covers the FinQA dataset construction and verification, common failure modes of frontier models, transfer to multi-table and general tool-use tasks, and ablations showing that simple data and binary rewards outperform more elaborate setups, since the real bottleneck is disciplined tool use rather than reasoning depth.

Artificial Intelligence

View All
Can Your AI Use Sensitive Data Safely? 5 Capabilities You Need

Can Your AI Use Sensitive Data Safely? 5 Capabilities You Need

Sensitive data gives AI its greatest value and its greatest risk. This piece walks through five foundational controls for using that data safely in AI systems, agents, and RAG pipelines: visibility across systems, automated classification, data residency and sovereignty governance, identity-based access control, and continuous audit evidence.

The Silent Failure in Every Multi-Agent System (with Vijoy Pandey)

The Silent Failure in Every Multi-Agent System (with Vijoy Pandey)

Vijoy Pande, SVP and GM of Cisco's incubation engine Outshift, argues that multi-agent AI systems fail silently because connected agents do not share meaning. He presents data showing cognitive failures in every multi-agent session analyzed, introduces the open-source SCOPE platform with ACCORD and CONCORD protocols for keeping agents aligned, describes a quantum network run on New York City fiber, and makes the case for hardware that computes on probabilities rather than bits.

Make Your AI Agents Predictable With Graph Engineering - Zachary Blumenfeld, Neo4j

Make Your AI Agents Predictable With Graph Engineering - Zachary Blumenfeld, Neo4j

A walkthrough of graph engineering, the practice of expressing agent logic as an explicit graph of nodes and routed state. It covers execution, context, and procedural graphs, how skills and decision traces can be compiled into portable graph-shaped skills, and a loan-approval demo showing gains in predictability, governance, and cost.

Technology

View All
What iPhone Packaging Reveals About the Robotics Opportunity

What iPhone Packaging Reveals About the Robotics Opportunity

Tutor Intelligence CEO Josh Gruenstein explains why robotics is a systems problem spanning AI, hardware, manufacturing, and customers, and how deploying robots into real factories and warehouses, with human tutors as backup, generates the data that makes them more capable. The discussion covers the company's own robot designs, its focus on small and mid-sized businesses, the economics of flexible robotic labor, and the implications for American manufacturing and supply chains.

Why Founders Are Betting Big on Factories, Mines, and Energy

Why Founders Are Betting Big on Factories, Mines, and Energy

Erin Price-Wright and Connor Love unpack the AD50 and the rebuilding of America's industrial base, covering how defense demand is financing manufacturing capacity for commercial markets, how AI is reshaping factory economics, how a new generation of founders applies lessons from SpaceX, Tesla, Anduril, and Palantir to mining, energy, and manufacturing, and why private capital is now willing to fund physical infrastructure before government demand is guaranteed.

Mark Cuban’s Plan to Make Healthcare Affordable

Mark Cuban’s Plan to Make Healthcare Affordable

Mark Cuban and Julie Yoo discuss how transparency, direct contracting, and AI could reshape healthcare economics, from Cost Plus Drugs and modular pod manufacturing to personalized medicine, the future of physicians, and advice for founders who want to use AI to learn rather than to stop thinking.

Recent Post

Hardware Realization and Implementation Security Evaluation of HQC, A NIST PQC Standard

Hardware Realization and Implementation Security Evaluation of HQC, A NIST PQC Standard

This talk by Sanjay Deshpande from Northwestern University explores the critical transition to Post-Quantum Cryptography (PQC) in response to the threat quantum computers pose to current public-key algorithms. It provides a deep dive into the Hamming Quasi-Cyclic (HQC) algorithm, a code-based candidate for NIST standardization. The session focuses on the challenges and innovations in creating efficient and secure hardware implementations of HQC, covering performance optimization for polynomial multiplication and countermeasures against side-channel attacks.

GeoMind: A Multi-Agent Framework for Geospatial Decision Support

GeoMind: A Multi-Agent Framework for Geospatial Decision Support

GeoMind is a multi-agent framework designed to empower non-technical users, such as disaster responders, to perform complex geospatial analysis using natural language. It bridges the gap between Large Language Models and advanced GIS workflows by employing a team of specialized AI agents that can query, join, and analyze multi-layered vector and raster data to provide timely, actionable insights during emergencies.

AI is critical for humanity’s survival: Cisco President on the AI revolution | Jeetu Patel

AI is critical for humanity’s survival: Cisco President on the AI revolution | Jeetu Patel

Jeetu Patel, President and CPO at Cisco, shares his frameworks for transforming a 90,000-person company to be AI-first, building great companies, and leading at scale. He discusses Cisco's critical role in the AI infrastructure buildout, the necessity of AI for humanity's future, and his counterintuitive principles on communication and strategy.

Learn Docker in a Month of Lunches • Elton Stoneman & Bret Fisher • GOTO 2026

Learn Docker in a Month of Lunches • Elton Stoneman & Bret Fisher • GOTO 2026

Docker educators Bret Fisher and Elton Stoneman discuss the second edition of Stoneman's book, "Learn Docker in a Month of Lunches". They explore why Docker fundamentals remain crucial in a Kubernetes-dominated world, the evolution of the container ecosystem over the past five years, and the key skills that differentiate a Docker expert from a beginner, such as multi-platform builds, security, and configuration management.

The #1 AI Agent on GitHub Was Never Read by Its Creator

The #1 AI Agent on GitHub Was Never Read by Its Creator

Jason Martin of HiddenLayer discusses the significant security vulnerabilities of OpenClaw, a viral open-source AI personal assistant. The analysis covers critical flaws like prompt injection, insecure defaults, and the potential for creating sophisticated botnets, offering key lessons for securing the next generation of autonomous AI agents.

How Capital is Powering the AI Infrastructure Buildout with Magnetar Capital's Neil Tiwari

How Capital is Powering the AI Infrastructure Buildout with Magnetar Capital's Neil Tiwari

Neil Tiwari of Magnetar Capital explains the creative debt structures and financial innovations fueling the multi-trillion dollar AI infrastructure buildout. He debunks the myths around GPU collateral, revealing that the real security lies in contracted cash flows from investment-grade partners, and details how the industry's bottlenecks are shifting from chips to power distribution, steel, and specialized labor.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

Get updates straight to your inbox. No spam, just useful content.