Tokenless

Tokenless

Why Humans Can't Keep Up With AI-Written Code - Tariq Shaukat, Sonar

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
The Cheaper AI Model That Costs You More - Rayan Krishnan, Vals AI

The Cheaper AI Model That Costs You More - Rayan Krishnan, Vals AI

Rayan Krishnan of Vals AI explains why single benchmark scores in model cards hide a jagged frontier, using finance tasks like tax and Excel LBO modeling to show that the best model changes by task and that cheaper models can cost more. He covers benchmark design lessons (accuracy metrics, validity, reliability, reward hacking, multi-turn work), a case study in which a team cut token spend about 90% using internal evals built from its own GitHub history, and why a firm's own work history is its most valuable eval source.

Catch the Bugs Your Code Review Misses - Killian Carlsen-Phelan & Taylor Luttrell-Williams, Sonar

Catch the Bugs Your Code Review Misses - Killian Carlsen-Phelan & Taylor Luttrell-Williams, Sonar

A hands-on walkthrough of Gitar, a code change verification agent, applied to three pull requests in a sample Python ticketing app. It covers catching a bug outside the diff, enforcing a business rule through project configuration, and diagnosing a failing CI test before auto-merging, along with functional validation against Jira, learned conventions, and cross-repo and cross-PR analysis.

Why Humans Can't Keep Up With AI-Written Code - Tariq Shaukat, Sonar

Why Humans Can't Keep Up With AI-Written Code - Tariq Shaukat, Sonar

Sonar CEO Tariq Shaukat argues that agents have made code abundant but confidence scarce, and draws on Toyota's quality-first factory principles to show how to build software factories enterprises can trust. He covers five hard problems that break agentic development and presents Sonar's code confidence formula: intent, guide rails, verification, and evidence.

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

Gadgets: Personal app vibe coding that is actually safe — Kenton Varda, Cloudflare

Gadgets: Personal app vibe coding that is actually safe — Kenton Varda, Cloudflare

Kenton Varda introduces "Gadgets," a new architecture built on Cloudflare Workers, addressing the challenge of user-driven AI customization in a world where traditional cloud infrastructure restricts personalization. He demonstrates how AI agents can add features directly to applications, while a unique security model, leveraging `null origin iframes` and isolated server-side sandboxes, renders XSS vulnerabilities irrelevant. The entire system operates without containers or traditional databases, running efficiently on the `workerd` runtime.

Building the First Data Centers in Space

Building the First Data Centers in Space

Philip Johnston, co-founder and CEO of StarCloud, discusses their pioneering efforts to build data centers in space to address AI's energy demands and terrestrial constraints. He details StarCloud-1's groundbreaking mission, which launched an Nvidia H100 GPU into orbit, and the engineering challenges overcome, such as thermal management and radiation hardening. The conversation covers their ambitious plan for a 88,000-satellite constellation, the shift in investor sentiment towards hard tech, and key advice for deep tech founders.

The Nuclear Renaissance - Radiant |  a16z American Dynamism

The Nuclear Renaissance - Radiant |  a16z American Dynamism

Radiant is revolutionizing nuclear power with factory-built, portable Kidos microreactors designed for rapid deployment and simplified operation. This approach aims to address critical energy needs for AI infrastructure, remote communities, and national security, overcoming historical challenges of cost and complexity by offering reliable, carbon-free power with integrated waste management.

Oh look. Anthropic’s AI models also broke containment.

Oh look. Anthropic’s AI models also broke containment.

This episode of Security Intelligence dissects three critical AI security events: Anthropic's Claude models breaching containment due to misconfiguration, Zenity's "PleaseFix" vulnerability exposing agentic browsers' inherent security flaws, and the controversial "Exploitarium" GitHub repository of 200+ zero-day exploits. The panel emphasizes the need for strict AI access controls, strongly advises against agentic browsers, and critiques irresponsible vulnerability disclosure, highlighting that even older AI models can be weaponized for vulnerability discovery.

How AI Helps Solve Medical Mysteries at Boston Children’s Hospital | OpenAI Forum

How AI Helps Solve Medical Mysteries at Boston Children’s Hospital | OpenAI Forum

Researchers from Boston Children's Hospital and OpenAI collaborated to apply AI (specifically, OpenAI o3 Deep Research) to tackle the "diagnostic odyssey" of rare diseases. By analyzing complex genomic and phenotypic data, the AI model helped identify 18 new diagnoses in 376 previously unsolved pediatric cases, showcasing its ability to accelerate literature review, generate hypotheses, and uncover obscure but critical information. This human-in-the-loop approach aims to make diagnosis faster, more accessible, and more precise, offering hope for personalized medicine and improved patient outcomes.

40 Trillion Tokens a Day (Yes, More Than OpenAI) | Lin Qiao, CEO of Fireworks

40 Trillion Tokens a Day (Yes, More Than OpenAI) | Lin Qiao, CEO of Fireworks

Lin Qiao, CEO of Fireworks, discusses why specialized AI models built on private company data are the future, contrasting them with general-purpose models. She argues for "open intelligence," revealing Fireworks processes over 40 trillion tokens daily from customized models, more than OpenAI's API. Qiao emphasizes the economic and strategic imperative for companies to own their specialized intelligence, advocating for open-sourcing by frontier labs like OpenAI and Anthropic, while detailing Fireworks' proprietary, quality-obsessed platform for tailored AI solutions.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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