Tokenless

Tokenless

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

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
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.

Your AI Pilots Won't Move the P&L. Here's What Will - Adam Nahari, Apollo

Your AI Pilots Won't Move the P&L. Here's What Will - Adam Nahari, Apollo

Most companies use AI, but few see it in their margins. Adam Nahari of Apollo Global Management argues that engineering is the smaller part of an AI transformation and lays out six moves, illustrated by an airline's crew-scheduling desk, for turning AI into measurable EBIT impact.

Technology

View All
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.

Exploits Now Beat Patches: Open Source Security in the AI Era - Patrick Smyth, Chainguard

Exploits Now Beat Patches: Open Source Security in the AI Era - Patrick Smyth, Chainguard

Patrick Smyth of Chainguard examines how frontier AI has compressed the time between vulnerability disclosure and exploitation, leaving 30-day remediation cycles obsolete. The talk covers AI-assisted attacks, waves of supply chain malware, four attack surfaces spanning malware, known CVEs, zero days, and side doors like CI/CD, developer laptops, and agent skills, and practical defenses including cooldown periods, faster CVE remediation, and signing artifacts with SLSA and Sigstore.

Recent Post

Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI

Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI

Maxime Labonne from Liquid AI shares a playbook for post-training frontier small models (under 1GB) for on-device deployment. The talk breaks down the LFM2.5 recipe, which includes on-policy preference alignment and agentic reinforcement learning, and addresses unique challenges at the 1B scale, such as capability interference and 'doom loops', offering concrete solutions to build efficient models for tasks like data extraction and tool use.

Why AI Infrastructure Is Everyone's Problem Now (with Linda Haviv)

Why AI Infrastructure Is Everyone's Problem Now (with Linda Haviv)

Linda Haviv discusses the evolving AI landscape, arguing that systems thinking is becoming more critical than coding. She highlights how non-linear career paths and domain-specific expertise provide a competitive edge, and explores how the democratization of technology is fueling a new wave of entrepreneurship and content creation for tech professionals.

Is open source safe? Featuring Mixture of Experts

Is open source safe? Featuring Mixture of Experts

AI and security experts debate the complex relationship between open source and AI, weighing the foundational role of open source in innovation against the significant security challenges of both proprietary and open models, and exploring the difference between 'secure' and 'securable' systems.

Building your own software factory — Eric Zakariasson, Cursor

Building your own software factory — Eric Zakariasson, Cursor

Eric Zakariasson from Cursor explains the shift from single-agent pair programming to managing a multi-agent "software factory". He outlines the practical steps required, from establishing a well-structured codebase with guardrails to adopting a managerial mindset that focuses on automation, asynchronous work, and scaling agent fleets to increase software development throughput and consistency.

What happens now that AI is good at math? — the OpenAI Podcast Ep. 17

What happens now that AI is good at math? — the OpenAI Podcast Ep. 17

OpenAI researchers Sébastien Bubeck and Ernest Ryu discuss the dramatic and surprising progress of AI in mathematics. They cover how models went from basic arithmetic to solving Olympiad-level and even 40-year-old open research problems, what this progress means for the future of science and AGI, and the evolving role of human researchers in an era of AI-accelerated discovery.

Why building eval platforms is hard — Phil Hetzel, Braintrust

Why building eval platforms is hard — Phil Hetzel, Braintrust

An evaluation platform is more than a simple test runner; it's a complex system for creating shared definitions of quality. This talk explores the evolution of eval platforms from basic spreadsheets to sophisticated, integrated systems, highlighting the hidden data and systems engineering challenges involved in making them credible, scalable, and usable for building trustworthy AI agents.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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