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

Compression at the Edge — Chris Alexiuk, NVIDIA

Compression at the Edge — Chris Alexiuk, NVIDIA

This panel discussion explores the critical role of model compression, particularly quantization, in democratizing AI. It delves into how massive models like GLM 5.2 can be shrunk by over 80% without equivalent performance loss, thanks to techniques like mixed-precision quantization and understanding uneven layer importance. The discussion covers NVIDIA's NVFP4 format, challenges posed by new model architectures, the preference for KL divergence over accuracy benchmarks, and the vision of future AI running efficiently on all local devices.

Garry Tan: "Personal AGI Is How You Stay Under Your Own Power"

Garry Tan: "Personal AGI Is How You Stay Under Your Own Power"

YC President Garry Tan introduces "Personal AGI," a concept where individuals own and train AI agents on their unique context, transforming personal productivity and startup creation. He shares his workflow, advocating for Markdown as code and emphasizing the critical importance of owning one's intellectual assets in the age of AI. The talk outlines a practical 5-step guide to building a personal AI system and explores the profound implications for innovation and individual empowerment.

The State of Model Routing — NVIDIA, Cognition, OpenRouter

The State of Model Routing — NVIDIA, Cognition, OpenRouter

A deep dive into model routing strategies for AI/ML production, featuring experts from Cognition, OpenRouter, and NVIDIA. Key topics include optimizing costs with multi-model systems, delegating tasks between frontier and smaller models, managing context efficiently (sidekicks, compaction), and adapting to dynamic task complexities. The panel discusses the fragility of naive routing, the cost implications of in-distribution vs. out-of-distribution tasks, and the evolution of auto-routers driven by real-world usage patterns like OpenClaw's heartbeats. Insights also cover NVIDIA's Flex Run for dynamic model sizing, hallucination probes for detecting model limitations, and the future of hybrid local/cloud routing and model collaboration.

How Open Source Became AI's Backbone | Inferact with a16z

How Open Source Became AI's Backbone | Inferact with a16z

Simon Mo, CEO of Inferact and lead maintainer of vLLM, discusses how open-source AI, exemplified by vLLM, transformed into critical infrastructure. The conversation highlights the technical complexities of serving LLMs, the evolving economics and licensing of open-weight models, the need for control over guardrails, and the rapidly disappearing capability gap between open and proprietary AI.

A Long Spring: 19 Years of Living with Your Past Mistakes • Arjen Poutsma • GOTO 2025

A Long Spring: 19 Years of Living with Your Past Mistakes • Arjen Poutsma • GOTO 2025

Arjen Poutsma, a Spring Framework veteran, reflects on 19 years of evolving the framework. He shares insights on API design from XML to functional programming, detailing anecdotes like bubble sort in MVC and the challenges of HTTP method enums. Poutsma emphasizes the critical role of diversity, empathy, humility, and restraint in open-source stewardship to maintain developer trust and foster innovation under constraints.

Chasing Trillion-Dollar Companies, Founder Ambition, Token Budgets, & Regulatory Capture

Chasing Trillion-Dollar Companies, Founder Ambition, Token Budgets, & Regulatory Capture

Elad and Sarah discuss the rapid rise of AI's multi-trillion-dollar companies, debating whether this growth is sustainable or an anomaly. They explore how founder ambition is shaped by fear of AI labs, optimal strategies for startup exits, and the psychological impact of impending AGI on researchers. Key bottlenecks like compute power, the emergence of an oligopoly, and the growing threat of regulatory capture—exemplified by California's tax policies—are also analyzed, highlighting the critical societal trade-off between safety and technological progress.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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