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

From Chat Fatigue to Instant Action // Donné Stevenson

From Chat Fatigue to Instant Action // Donné Stevenson

A discussion on the evolution of AI agent interaction, moving beyond simple text-based chat to create intuitive, GUI-driven experiences. The talk covers the practical challenges and solutions in building an impactful agent for busy professionals, focusing on quick actions, efficient data streaming, and enhanced interactivity.

Context Engineering 2.0: MCP, Agentic RAG & Memory // Simba Khadder

Context Engineering 2.0: MCP, Agentic RAG & Memory // Simba Khadder

Simba Khadder of Redis introduces Context Engineering 2.0, a new paradigm for AI agents that unifies structured data, unstructured data (RAG), and memory into a single, schema-driven surface. He critiques current methods like Text-to-SQL and direct API wrapping, proposing a unified context engine to provide reliable, observable, and performant data access for agents.

Enterprise-ready MCP // Jiquan Ngiam

Enterprise-ready MCP // Jiquan Ngiam

Jiquan Ngiam, CEO of MintMCP, discusses the paradigm shift from static programs to dynamic AI agents, outlining the significant security risks involved—supply chain vulnerabilities, third-party data poisoning, and inadvertent agent behaviors—and presents a three-pronged strategy for enterprise readiness: comprehensive monitoring, preventative guardrails, and secure, role-based deployment of Model Context Protocols (MCPs).

Open vs Closed Source Agent Infra?

Open vs Closed Source Agent Infra?

This panel delves into the strategic implementation of open-source, community-driven agentic stacks, balancing the benefits of open-source frameworks and models for rapid iteration, cost-efficiency, and compliance against the complexities of abstraction and debugging in production environments. Experts from NVIDIA, Stacklok, and Prosus discuss when to adopt open source, challenges in framework choice, the critical need for robust observability, and the role of no-code solutions for diverse user groups, emphasizing the importance of aligning tooling decisions with specific use cases and organizational needs.

Efficient Homomorphic Integer Computer from CKKS

Efficient Homomorphic Integer Computer from CKKS

This talk introduces Discrete CKKS, a framework that extends the approximate FHE scheme CKKS to support exact integer arithmetic. It achieves this through a hybrid bootstrapping technique that both cleans noise and raises the modulus, enabling a high-throughput, vectorized engine for general-purpose discrete computations on encrypted data.

How A Team Of 7 Keeps Breaking AI Benchmark Records

How A Team Of 7 Keeps Breaking AI Benchmark Records

Poetiq, a startup by former DeepMind researchers, has developed a recursive self-improvement meta-system that builds "reasoning harnesses" on top of existing LLMs. This approach avoids the costly "fine-tuning trap" and has achieved state-of-the-art results on benchmarks like ARC-AGI and Humanity's Last Exam by automatically optimizing prompts and discovering novel reasoning strategies.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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