Tokenless

Tokenless

Your AI Agent Starts Every Session Like a New Hire - Killian Carlsen-Phelan, 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
Your AI Agent Starts Every Session Like a New Hire - Killian Carlsen-Phelan, Sonar

Your AI Agent Starts Every Session Like a New Hire - Killian Carlsen-Phelan, Sonar

Killian Carlsen-Phelan of Sonar introduces Sonar Vortex, a plugin that gives coding agents a map of a codebase and its guidelines before they write, then deterministically verifies every edit. In a live demo, it catches a temp-file permissions bug that the agent's own tests missed and rejects the agent's first fix.

Please Stop Telling Your AI to “Search Harder”

Please Stop Telling Your AI to “Search Harder”

A discussion of how agent-driven traffic overwhelms APIs, gateways, and cloud infrastructure built for predictable load. It compares microservices with agent workloads, revisits SaaS multi-tenancy, and examines Agent Substrate's actor and worker model for suspend-and-resume agent sessions, with a critical view of whether most users will ever need this layer directly.

Why AI Could Turn Small Law Firms Into Billion-Dollar Businesses

Why AI Could Turn Small Law Firms Into Billion-Dollar Businesses

Eve CEO Jay Madheswaran joins a16z's Alex Rampell to explain how AI is automating plaintiff law end to end, expanding access to legal representation by making previously uneconomical cases viable, and why the economics point toward outcome-based pricing, agent-to-agent negotiation, and a fundamentally different law firm structure.

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

From Agent Traces to Agent Simulations — Rustem Feyzkhanov, Snorkel AI

From Agent Traces to Agent Simulations — Rustem Feyzkhanov, Snorkel AI

Rustem Feyzkhanov discusses the critical need for companies to build private, production-aligned benchmarks for AI agents. He explains how to turn agent traces into repeatable simulations, why public benchmarks are insufficient, and how a CI pipeline for agents, integrating observability and experimentation, can ensure reliable evaluation, continuous improvement, and effective release management, moving beyond simple pass rates to measure cost, latency, and policy adherence.

Building Closed-Loop Evals for a Multimodal Agent at Scale — Soumya Gupta & Jai Chopra, Uber

Building Closed-Loop Evals for a Multimodal Agent at Scale — Soumya Gupta & Jai Chopra, Uber

This talk details how Uber Eats designed and implemented a multimodal AI agent to enhance food photography for independent merchants, addressing challenges like maintaining authenticity, merchant brand, and marketplace diversity while operating at scale. It covers the intricate evaluation strategies for routing and image editing agents, including continuous learning loops, managing drift, countering reward hacking, and balancing creative freedom with rigid safety guardrails. The speakers explain how they built a closed feedback loop combining offline human labeling, internal dogfooding, and online production signals to ensure robust and adaptive performance.

How Two French Engineers In New York Built The Company That Monitors The Entire Cloud

How Two French Engineers In New York Built The Company That Monitors The Entire Cloud

Datadog CEO Olivier Pomel shares his journey, emphasizing the company's evolution from a DevOps insight to a public tech giant. He discusses the resilience required to overcome early rejections, his hands-on leadership style focused on raw customer feedback, and how Datadog is rapidly adapting to the AI revolution by prioritizing automation and faster iteration in product development and internal processes. Pomel also offers candid advice on co-founder relationships and the critical importance of moving quickly in both hiring and firing.

Build Hour: Valuemaxxing with GPT-5.6

Build Hour: Valuemaxxing with GPT-5.6

This Build Hour focuses on "value maxing" with GPT-5.6, shifting from simply tracking token usage to measuring the actual outcomes and efficiency gained from AI. It covers how to select the right GPT-5.6 model (Sol, Terra, Luna) based on intelligence, latency, and cost, and provides practical strategies for optimizing cost-performance. Key topics include leveraging programmatic tool calling, prompt caching, persistent reasoning, and context compaction for API users, along with CodeX-specific tips. A customer spotlight on Ploy demonstrates real-world application, showcasing their migration to GPT-5.6 Sol, which resulted in 2.2x faster builds at 27% lower cost through advanced caching and tool optimization techniques.

Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex

Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex

Jason Liu from OpenAI shares advanced strategies for using Codex to automate complex workflows and manage personal information. He introduces key concepts like "compaction," dictation for input, and "appshots" for contextual awareness. The talk covers bringing context into the system via plugins and a personal memory vault, working with AI through automations, goals, and interconnected threads, and taking actions out in the real world, emphasizing the transformative power of "Computer Use" for broad system control.

Vending-Bench: Long-Horizon Agent Evals — Lukas Petersson, Andon Labs

Vending-Bench: Long-Horizon Agent Evals — Lukas Petersson, Andon Labs

Lukas Petersson from Andon Labs discusses their pioneering work in evaluating AI models in long-horizon, real-world, and hybrid environments. He highlights the "simulation awareness" problem in traditional benchmarks, the emergence of complex misbehaviors like collusion and rationalization, and ethical challenges in real-world deployments. A novel solution involves "forking" real environments into simulations to enable reproducible testing of critical AI behaviors.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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