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
Voice AI Where One Wrong Question Breaks the Rules - Shiv Indap, Upstart & Brooke Hopkins, Coval

Voice AI Where One Wrong Question Breaks the Rules - Shiv Indap, Upstart & Brooke Hopkins, Coval

Shiv Indap of Upstart and Brooke Hopkins of Coval walk through automating loan verification calls in a heavily regulated lending environment. They cover the compliance traps that shape the agent's behavior, moving human review beyond a Google Sheet, and raising LLM judge agreement with human reviewers from 33% to 92%. The talk then lays out a continuous loop of live monitoring, human review queues, simulation-based testing of fixes, and self-healing agents, with humans signing off on every change.

Building ChatGPT for Finance — Joseph Kim, OpenAI's Head of Financial Services

Building ChatGPT for Finance — Joseph Kim, OpenAI's Head of Financial Services

Joseph Kim of OpenAI discusses building ChatGPT for Financial Services on a general-purpose model: upstream financial reasoning training, bundling market data after MCP reliability tests, plugin primitives startups can reuse, human-in-the-loop review, training judgment and taste via reward models, and the difficulty of building financial evals.

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.

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

AI Can't Learn The Way Humans Do - This Could Fix That

AI Can't Learn The Way Humans Do - This Could Fix That

This discussion explores world models as a promising path to solving sample efficiency in AI and achieving AGI. It contrasts deterministic control (Newtonian physics) with stochastic environments (RL), explaining the challenges posed by large action spaces in Go, self-driving, and robotics. The episode delves into how synthetic data, video diffusion models, and latent space architectures like JEPA are making world models practical, while also highlighting remaining open problems in physics modeling, real-time adaptation, and rich sensory integration.

Fable 5 as Advisor: Anthropic's Two-Model Pattern for Smarter, Cheaper Agents (Ep. 1010)

Fable 5 as Advisor: Anthropic's Two-Model Pattern for Smarter, Cheaper Agents (Ep. 1010)

The episode explores Anthropic's "advisor strategy," a novel AI agent pattern that combines a fast, cheap "executor" model with a frontier-class "advisor" model. This allows for mid-task consultation within a single API call, resolving the tension between cost and capability. Benchmarks show simultaneous improvements in quality and cost reduction, demonstrating that AI progress is shifting towards intelligent model composition rather than just larger models.

Thinking Machines Lab drops Inkling & Meta’s Muse Spark 1.1

Thinking Machines Lab drops Inkling & Meta’s Muse Spark 1.1

This episode covers Thinking Machines' Inkling, an open-source, customizable model prioritizing architecture over benchmarks; Meta's Muse Spark 1.1, positioned for agent orchestration and enterprise use; OpenAI's GPT-5.6 Sol's 8% score on ARC-AGI-3, reigniting AGI debates; and Anthropic's "J-space" paper, exploring internal model reasoning and its implications for AI safety and interpretability.

Closing Keynote: Garry Tan, Y Combinator

Closing Keynote: Garry Tan, Y Combinator

Garry Tan, President of Y Combinator, details how AI-native companies are achieving unprecedented productivity and scale with lean teams. He introduces the concept of "wiring the work" by treating AI as a workforce where organizational components are encoded into markdown "skill files." Tan explains how "company brains" act as a library and librarian, managing institutional knowledge to overcome human memory limits. He emphasizes the discipline of "skillifying" every task to ensure continuous learning and calls on founders to build these new AI-native infrastructures to "boil the ocean"—tackling previously insurmountable problems.

Imagination Engineering — Eve Bouffard, Head of Design, Y Combinator

Imagination Engineering — Eve Bouffard, Head of Design, Y Combinator

Eve Bouffard of Y Combinator introduces "Imagination Engineering," arguing that powerful AI shifts the human challenge from execution to ideation. She showcases personal experiments like an AI-generated website from her public thoughts, a tool visualizing historical geniuses, and custom productivity aids. Bouffard highlights AI's role as a "rocket ship for the mind," enabling rapid learning and software creation on demand.

Learning Genetic Perturbation Effects at Single-Cell Resolution for Virtual Cells

Learning Genetic Perturbation Effects at Single-Cell Resolution for Virtual Cells

Jiaqi Zhang's talk focuses on advancing causal discovery and perturbational modeling for gene networks, crucial for therapeutic insights. She introduces theoretical guarantees for learning latent causal variables and presents MORPH, a VAE-based framework that predicts the effects of novel and combinatorial gene perturbations by integrating diverse prior biological knowledge and using distributional loss for training. The model has demonstrated success in guiding experimental design, including identifying novel T-cell regulators for cancer immunotherapy, highlighting its potential to accelerate biological discovery and drug development.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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