Tokenless

Tokenless

Your Company Should Train Its Own AI Models - Will Brown, Prime Intellect

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
Your Company Should Train Its Own AI Models - Will Brown, Prime Intellect

Your Company Should Train Its Own AI Models - Will Brown, Prime Intellect

Will Brown of Prime Intellect argues that organizations should train models on their own traces, feedback, and workflows so that agents learn institutional knowledge the way human coworkers do. The talk covers evals as test cases, decision models and routing, widget-style interfaces that turn human decisions into training data, and nightly training runs toward self-improving organizations.

A Valid Key Let an AI Agent Delete Production - Sagar Batchu, Speakeasy

A Valid Key Let an AI Agent Delete Production - Sagar Batchu, Speakeasy

A coding agent with valid credentials deleted a production database and its backup while trying to fix a staging issue. Sagar Batchu of Speakeasy uses the incident to lay out a control layer for agents in regulated industries, where every action is tied to an identity, checked against policy in real time, bounded by its owner's rights, and recorded for compliance.

AI Writes Code Faster Than Your Team Can Review It - Andrew Norrish, Sourcegraph

AI Writes Code Faster Than Your Team Can Review It - Andrew Norrish, Sourcegraph

AI has shifted the bottleneck in software delivery from writing code to reviewing it, and SREs are absorbing the incidents that unreviewed AI code produces. This talk examines why trust in AI-generated code is lagging, why SRE and platform teams are best placed to respond, and how code search and a code graph context engine support investigation, prevention, and remediation across large codebases.

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

Architecture for Flow • Susanne Kaiser & James Lewis

Architecture for Flow • Susanne Kaiser & James Lewis

In an interview with James Lewis, Susanne Kaiser discusses her book "Architecture for Flow," which synthesizes Domain-Driven Design, Wardley Mapping, and Team Topologies. She explains how this holistic approach helps design adaptive socio-technical systems by starting with the problem space, visualizing the value chain, and aligning team structures to the software architecture, all guided by her practical "Architecture for Flow Canvas."

The Future of Search: Agents, RAG, and Why Retrieval Still Matters — Simon Eskildsen, Turbopuffer

The Future of Search: Agents, RAG, and Why Retrieval Still Matters — Simon Eskildsen, Turbopuffer

Simon Hørup Eskildsen, founder of turbopuffer, shares his journey from scaling Shopify's infrastructure to creating a new search engine for the AI era. He discusses how a prohibitively expensive experiment at Readwise inspired him to build a cost-effective vector search solution based on object storage and NVMe. Eskildsen breaks down turbopuffer's architecture, its role in cutting costs for companies like Cursor and Notion, his philosophy on building a 'P99' engineering team, and how agentic workloads are changing the future of retrieval.

Alex Karp on Palantir, AI Weapons, & American Domination | The a16z Show

Alex Karp on Palantir, AI Weapons, & American Domination | The a16z Show

Alex Karp, CEO of Palantir, discusses the critical role of technology in national defense, warns Silicon Valley of a political backlash if it fails to support the military, and argues that America's key advantage in the AI race is its ability to cultivate and protect neurodiverse, unconventional talent.

Master Software Architecture: From Simplicity to Complexity • Maciej «MJ» Jedrzejewski • GOTO 2025

Master Software Architecture: From Simplicity to Complexity • Maciej «MJ» Jedrzejewski • GOTO 2025

This presentation by Maciej Jedrzejewski explores the concept of evolutionary software architecture, arguing that architecture is not a static, upfront design but a continuous process. It delves into the cognitive biases that lead to over-engineering, emphasizes the critical role of context, and provides a practical four-step model for evolving systems from simplicity to complexity.

What Are Hierarchical AI Agents? Solving Context & Task Challenges

What Are Hierarchical AI Agents? Solving Context & Task Challenges

Explores the challenges of single AI agents, such as context dilution and tool overload, and introduces hierarchical AI agents as a solution. This summary details the structure, benefits, and limitations of multi-agent systems for more scalable and efficient AI workflows.

From Coder to Manager: Navigating the Shift to Agentic Engineering with Notion Co-Founder Simon Last

From Coder to Manager: Navigating the Shift to Agentic Engineering with Notion Co-Founder Simon Last

Notion's Co-Founder, Simon Last, discusses their evolution from a writing assistant to a platform for custom AI agents. He covers the technical hurdles of semantic indexing, the internal shift toward using coding agents to build Notion, and the fundamental transition from a tool where humans do the work to one where humans manage a swarm of agents.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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