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
How to Decide What Your AI Agent Should Remember - Wojciech Pluta, Oracle

How to Decide What Your AI Agent Should Remember - Wojciech Pluta, Oracle

Wojciech Pluta, head of technical marketing for Oracle AI Database, argues that RAG gives agents a read path while memory gives them a write path, and that the write path is where business value lives. He explains memory promotion, a pipeline that admits, rejects, or escalates candidate memories, and demonstrates it with a mortgage agent that remembers preferences across sessions while refusing unsafe rules. The talk also covers short-term, long-term, and shared memory, why databases are a strong storage layer, and the context card that keeps prompts lean.

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.

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

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.

Opencode CEO: Blocked, 20X Growth in 6 Months, Building the Coding Agent for the World

Opencode CEO: Blocked, 20X Growth in 6 Months, Building the Coding Agent for the World

Jay V, founder and CEO of Opencode, shares insights into the explosive growth of his platform, an open-source alternative to proprietary coding agents. He details Opencode's journey to 13 million monthly active users and 7 trillion tokens processed daily, attributing its rapid rise partly to an unexpected controversy with Anthropic and the maturing open-source model ecosystem. The discussion delves into global user adoption, the economic shift in AI token consumption, and how Opencode's strategic product design, rooted in 16 years of entrepreneurial persistence, positions it as a critical marketplace for diverse AI models, serving both individual developers and Fortune 500 companies.

Hugging Face breach: OpenAI’s model breaks containment

Hugging Face breach: OpenAI’s model breaks containment

This episode of Mixture of Experts explores pivotal AI developments: OpenAI's model breaching containment, Claude's Fable disproving a mathematical conjecture, Moonshot AI's massive 2.8 trillion parameter Kimi K3, and Google's shift to smaller, more efficient Gemini Flash models. The panel discusses AI security, its role in scientific discovery, and the evolving market strategies for model deployment, highlighting the tension between scale and efficiency.

Training Frontier Models to Out-Think Hackers — Uri Rolls, Arithmetic & Thom Wolf, Hugging Face

Training Frontier Models to Out-Think Hackers — Uri Rolls, Arithmetic & Thom Wolf, Hugging Face

Thom Wolf and Uri Rolls discuss the critical role of AI in cybersecurity, presenting a new benchmark called Masov. They argue that while frontier models excel at reconnaissance, they lack the sophisticated reasoning to exploit complex, logic-based zero-day vulnerabilities, such as a Keycloak name-versus-ID exploit. The solution, they propose, lies in high-quality, open-source AI models trained on real-world zero-day data to enable defenders to outpace attackers and build a new, AI-native security stack.

The Unreasonable Effectiveness of Separating the Task from the Model — Maxime Rivest, DSPy

The Unreasonable Effectiveness of Separating the Task from the Model — Maxime Rivest, DSPy

DSPy emphasizes separating task definition from model implementation using a "Signature" (inputs/outputs) to enable flexible, optimizable, and scalable AI programs. The framework relies on three pillars—instructions (specs), hard constraints (code), and examples (evals)—to fully specify tasks. DSPy 4.0 introduces DSPy Flex for learning program harnesses and Qualitative Learning for automated, feedback-driven evaluation refinement, offering significant benefits for enterprise applications and addressing "last-mile learning" for future AI systems.

Notion's Token Town — Sarah Sachs, Notion

Notion's Token Town — Sarah Sachs, Notion

Sarah Sachs, Head of AI Engineering at Notion, discusses the economic traps of AI model contracts and advocates for a "win on product" strategy. She details how Notion maintains optionality and leverage by treating suppliers as competitors, implementing a model-agnostic "AI Switzerland" approach with an auto model, leveraging open-weight models, and prioritizing data flywheels and orchestration over token economics to build sustainable AI products.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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