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
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.

Your AI Agents Shouldn't Care Where They Run - Nikhil Harithas, Factory

Your AI Agents Shouldn't Care Where They Run - Nikhil Harithas, Factory

Factory's Nikhil Harithas explains how Droid, their coding agent, was rebuilt to run on any compute inside a customer's own cloud. The talk covers the Open Compute abstraction, the compute gateway and outbound-only relay design, bring-your-own-key model calls, snapshots and forking for agent swarms, and the operational hard parts of managing compute for long-running agents in regulated enterprises.

Better Search Took This AI Agent From 36% to 98% Accuracy - Aamir Shakir, Mixedbread

Better Search Took This AI Agent From 36% to 98% Accuracy - Aamir Shakir, Mixedbread

Aamir Shakir of Mixedbread argues that the main limit on agent performance is access to the right data, not model intelligence. He explains why OCR, chunking, single-vector embeddings, and vector databases lose information at each step, and presents a late-interaction, multimodal retrieval approach that embeds document pages visually, with a live demo on Intel earnings reports and a hedge fund case study that raised answer accuracy from 36% to 98%.

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

This Is The Next Industry AI Will Disrupt

This Is The Next Industry AI Will Disrupt

Onshore founder Dominic Vitucci discusses how AI is causing a tectonic shift in the accounting industry, moving from a model based on billable hours to one of technology-driven outcomes, and what this means for the future of the profession and the legacy firms that dominate it.

OWASP's Top 10 Ways to Attack LLMs: AI Vulnerabilities Exposed

OWASP's Top 10 Ways to Attack LLMs: AI Vulnerabilities Exposed

A detailed breakdown of the updated OWASP Top 10 vulnerabilities for Large Language Models (LLMs), explaining threats like prompt injection, data poisoning, and supply chain risks, along with practical defense strategies.

AI Won't Replace You—But Someone Using AI Will

AI Won't Replace You—But Someone Using AI Will

In this episode, Ben Lorica and Evangelos Simoudis discuss how AI is fundamentally reshaping the modern workplace. They explore the necessary evolution of knowledge work, from a focus on routine execution to problem definition and spec-driven development, and outline the critical skills professionals must cultivate—including rapid experimentation, AI agent orchestration, and systems thinking—to remain valuable and navigate a more volatile labor market.

CROSS — Leveraging AI ASICs for Homomorphic Encryption

CROSS — Leveraging AI ASICs for Homomorphic Encryption

The talk presents CROSS and Morph, two compiler frameworks that enable existing AI accelerators, like Google's TPUs, to efficiently execute cryptographic workloads. CROSS focuses on Homomorphic Encryption (HE) and Morph on Zero-Knowledge Proofs (ZKP), demonstrating how to transform high-precision modular arithmetic into low-precision matrix operations that TPUs excel at, thereby achieving state-of-the-art performance and energy efficiency without any hardware modifications.

Efficient Distributed Orthonormal Optimizers for Large-Scale Training

Efficient Distributed Orthonormal Optimizers for Large-Scale Training

Kwangjun Ahn from Microsoft Research provides a technical overview of orthonormal optimizers (like Muon and Dion2), a new class of algorithms for large-scale AI model training that are emerging as powerful successors to AdamW. The talk covers their theoretical foundations, empirical benefits, distributed implementation strategies, and practical guidelines for integration into modern training pipelines.

Inside Perplexity Computer’s agent platform

Inside Perplexity Computer’s agent platform

Experts on the Mixture of Experts podcast analyze Perplexity Computer's pivot to agent orchestration and debate its closed-system approach versus open alternatives like OpenClaw. They also discuss Anthropic's new memory import feature for Claude, questioning if memory is still a competitive moat, and explore NullClaw, a minimalist agent framework that sparks a conversation about the future of edge-based agent swarms. Finally, they tackle the controversial debut of Tilly Norwood, the world's first AI actor, and debate the implications for the entertainment industry and the personification of AI.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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