Tokenless

Tokenless

Agents That Self Improve While You Sleep - Fuad Ali, Arize AI

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
How a Trading Firm Ships New AI Models the Same Day - Noyan Tokgozoglu, Optiver

How a Trading Firm Ships New AI Models the Same Day - Noyan Tokgozoglu, Optiver

A look at how Optiver, a proprietary trading firm, runs an on-prem AI platform where every model, agent, and harness decision has to show results in P&L within hours. Topics include the inference gateway, same-day adoption of frontier models, the meta harness design, and efforts to bring AI spend back under control.

Agents That Self Improve While You Sleep - Fuad Ali, Arize AI

Agents That Self Improve While You Sleep - Fuad Ali, Arize AI

A workshop on building a self-improvement loop for AI agents: tracing production traces, using an always-on agent to file deduplicated issues, turning failures into evals and regression datasets, proving fixes with experiments, and keeping humans at the highest-leverage review points.

How to Build Voice Agents That Don't Fall Apart When You Interrupt - Jesse Hall, LiveKit

How to Build Voice Agents That Don't Fall Apart When You Interrupt - Jesse Hall, LiveKit

Jesse Hall of LiveKit explains how to build voice agents for financial services that feel human rather than robotic. The talk covers why model leaderboards mislead for real-time conversations, why time to first audio and time to first sentence matter more than first byte or first token, and how async tool calls keep a conversation flowing during slow back-end work. It also covers audio-aware turn detection, the roughly 1.5-second latency budget, and benchmarking your own stack with simulated callers.

Technology

View All
What will computer chips look like in 2045?

What will computer chips look like in 2045?

Intel's leadership walks through how advanced process nodes are brought to volume, from yield learning and the lessons of 10nm to the shift from planar transistors to gate-all-around, High-NA EUV, backside power, and CFET. The discussion widens to the chip-to-chip bottleneck that hybrid bonding targets, the supply limits on EUV tooling as AI compute demand grows, and the economics that make foundry scale decisive.

Former Intel CEO: Why This is the Best Time to Build Hardware

Former Intel CEO: Why This is the Best Time to Build Hardware

Pat Gelsinger joins a16z's Raghu Raghuram and Guido Appenzeller to discuss how AI is reshaping chip design, why design speed alone will not fix semiconductor bottlenecks, and why power and energy capacity may ultimately limit AI growth. The conversation covers HBM and memory innovation, stacking limits, the shift from copper to optics, consolidation among AI chip startups, and what a VMware for AI agents might look like.

Built Together: Inside the Dell + CoreWeave Engineering Partnership Powering Next-Gen AI

Built Together: Inside the Dell + CoreWeave Engineering Partnership Powering Next-Gen AI

A candid panel between Dell and CoreWeave leaders on co-engineering GB200, GB300, and Vera Rubin rack-scale AI platforms. The discussion covers why early access and stabilization matter in the AI arms race, how the industry moved from server-level to rack-as-computer architecture, and how joint development, standardized Redfish tooling, and shifting diagnostics left have enabled scale. It closes with where rack-scale infrastructure is heading toward pods, denser heterogeneous systems, and the need for automation in liquid cooling and power.

Recent Post

Self-replicating AI, your doctor’s chatbot & agents at dinner

Self-replicating AI, your doctor’s chatbot & agents at dinner

A look at three developments shaping the near future of AI: Anthropic's research on small models that could copy themselves across cheap consumer devices, a JAMA study showing how doctors are adopting clinical chatbots for treatment decisions, and an experiment in which AI agents booked a founders' dinner and then networked with one another. The panel weighs security risks in the home, the trade-offs of speed versus verification in medicine, and how much autonomy agents should have when dealing with other agents.

A Bank Trained Its Own Foundation Model to Catch Fraud — Freddy Lecue, Wells Fargo

A Bank Trained Its Own Foundation Model to Catch Fraud — Freddy Lecue, Wells Fargo

Wells Fargo pre-trained a transformer from scratch on billions of customer transactions rather than words, then fine-tuned it for fraud detection, credit decisions, anti-money laundering and marketing. The talk covers how tabular transaction data was tokenized, the model's size and training setup, and results that beat the production XGBoost fraud model on both detection and false positives while meeting real-time latency requirements.

How to Let AI Agents Sign Up for Your App Safely — Isabelle Williams, WorkOS

How to Let AI Agents Sign Up for Your App Safely — Isabelle Williams, WorkOS

Isabelle Williams of WorkOS demonstrates how to make an application ready for agent users, using a travel app called Waypoint. She covers the auth.md protocol for anonymous agent access and claim flows, ID-JAG identity assertions that let an agent's provider vouch for a user without a signup form, and scoped, revocable agent tokens that keep agent permissions auditable and bounded.

Don't Trust Your AI Agents. Test Them Like a Scientist — Stephanie Jarmak, Omni Analytics

Don't Trust Your AI Agents. Test Them Like a Scientist — Stephanie Jarmak, Omni Analytics

Stephanie Jarmak, who moved from astronomy into building coding benchmarks and agent evals, argues that most agent evaluations are easy to misread. She covers how harness choice can swamp model differences, why public benchmarks serve shortlisting rather than decisions, how to design experiment-style evals with realistic tasks, repeated runs, and full traces, and how to set quality gates, manage human review load, verify agent records, and treat production as the final test.

Why AI Startups Will Disappear Without Compute Markets — Evan Conrad, San Francisco Compute

Why AI Startups Will Disappear Without Compute Markets — Evan Conrad, San Francisco Compute

Evan Conrad explains how San Francisco Compute went from an AI lab forced to sublease its own GPU cluster to an operator of supercomputers and a market for compute. He lays out the chain of risks facing new labs and inference companies, from sold-out capacity and oversized deposits to late, broken clusters and unpredictable demand, and argues that these form one credit-driven risk problem that a working compute market must solve.

Better AI Models Won't Fix Your Engineering Team — Nicholas Arcolano, Jellyfish

Better AI Models Won't Fix Your Engineering Team — Nicholas Arcolano, Jellyfish

Nicholas Arcolano of Jellyfish uses data from about 50,000 engineers across 447 companies to test what really drives AI coding output. A natural experiment forcing users onto Grok barely moved merged PRs. The analysis breaks throughput into tool, skill use, token consumption, company and team, and individual engineer, finding the individual and organization matter far more than the model.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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