Tokenless

Tokenless

The Right Model for Each Coding Task

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
Our Smaller Model Beat Opus on Finance Tasks - Alexander Shevchenko, Ramp

Our Smaller Model Beat Opus on Finance Tasks - Alexander Shevchenko, Ramp

Alexander Shevchenko of Ramp Labs explains why an application company keeps running applied research rather than waiting for the next frontier model, and walks through three projects in production: a post-trained Qwen 3.5 specialist for financial question answering at Haiku-level latency, KV cache cartridges that prepare agents with far more context ahead of time, and a 10,000-agent swarm that pen-tested Ramp and found seven high-severity vulnerabilities using cheaper open-weight models.

AI Labs Will Trap You or Replace You - Dillon Rolnick, Nous Research

AI Labs Will Trap You or Replace You - Dillon Rolnick, Nous Research

Nous Research CEO Dillon Rolnick argues that as AI models commoditize, frontier labs will try to recoup their enormous investments by locking businesses into their platforms or competing directly in lucrative sectors like finance. He contends that proprietary software moats are disappearing, that agents behave more like operating systems than chatbots, and that companies should build on open foundations they own, such as Hermes Agent, so they can swap models and inherit new capabilities.

Robots Will Be Trained on Video Games - Pim de Witte, General Intuition

Robots Will Be Trained on Video Games - Pim de Witte, General Intuition

Pim de Witte of General Intuition argues that models acting in space and time should be built differently from turn-based LLMs. Their continuous frames-in, actions-out model is trained on Medal game recordings, since game controllers already drive most robots, and it can play games and control more than ten robot types. The talk covers world models, action density, applications such as accessibility and UX, the difference from JEPA, and upcoming early access and hackathons.

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

Why AI Agents Forget Everything (And How To Fix That)

Why AI Agents Forget Everything (And How To Fix That)

Mem0 is building a model-neutral, persistent memory layer for AI agents to solve the fundamental statelessness of LLMs. Co-founders Taranjeet Singh and Deshraj Yadav discuss their hybrid memory architecture, which reduces cost and latency compared to context stuffing, and their vision for a future where user memory is portable across all AI applications.

The new AI race: Enterprise innovation in 2026

The new AI race: Enterprise innovation in 2026

Experts discuss OpenAI's new ad model for ChatGPT, the breakout moment for agentic coding with Claude Code, IBM's "Enterprise in 2030" report on the shift from AI efficiency to innovation, and Hugging Face's new "Open Responses" standard for agent APIs.

Abstraction & Idealization: AI's Plato Problem [Mazviita Chirimuuta]

Abstraction & Idealization: AI's Plato Problem [Mazviita Chirimuuta]

Professor Mazviita Chirimuuta discusses the philosophical underpinnings of neuroscience, challenging the brain-as-computer metaphor. She introduces 'haptic realism'—a view of knowledge as interactive and constructed—and argues for the inseparability of embodiment, finitude, and true understanding in both humans and AI.

The ML Technique Every Founder Should Know

The ML Technique Every Founder Should Know

YC Visiting Partner Francois Chaubard and YC General Partner Ankit Gupta break down diffusion, the machine learning framework behind generative AI models like Sora and Midjourney. They discuss its core principles, trace its evolution from complex KL-divergence methods to the elegant simplicity of flow matching, and explore its vast applications beyond images, from protein folding to robotics, arguing it's a key component for future AI systems.

Effect Oriented Programming • Bill Frasure, Bruce Eckel, James Ward & Andrew Harmel-Law • GOTO 2026

Effect Oriented Programming • Bill Frasure, Bruce Eckel, James Ward & Andrew Harmel-Law • GOTO 2026

Authors Bill Frasure, Bruce Eckel, and James Ward discuss the core concepts of Effect-Oriented Programming. They explain how effects are composable operations that encapsulate side effects and defer execution, allowing developers to manage unpredictability with compiler-checked types. The conversation covers ZIO, the expansion of effect systems into languages like TypeScript and Kotlin, and their unique, constraint-driven writing process.

No Priors Live: Building Durable Software in the AI Age with MongoDB President & CEO CJ Desai

No Priors Live: Building Durable Software in the AI Age with MongoDB President & CEO CJ Desai

CJ Desai, CEO of MongoDB, discusses why platforms, not products, are the key to long-term success in the software industry, especially in the age of AI. He explores the shifting landscape of enterprise software, the reality of AI adoption in Fortune 500 companies, and what truly constitutes a "moat" when software can be generated on demand.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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