Tokenless

Why We Rebuilt Microsoft Office From Scratch for AI Agents - Yijia Liang, Compound AI

Nov 01, 2026

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

Oct 13, 2026

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.

Oct 10, 2026

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.

Oct 10, 2026

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

Nov 01, 2026

Why We Rebuilt Microsoft Office From Scratch for AI Agents - Yijia Liang, Compound AI

Yijia Liang, founder of Compound and former finance analyst, explains why personal agents succeeded and what finance needs beyond them: multiplayer agents with their own inboxes, a headless Office engine rebuilt with agents, and agent swarms that navigate massive data rooms and models while keeping every output grounded in citations.

Nov 01, 2026

Most of Your Docs Readers Are Now AI Agents - Hahnbee Lee, Mintlify & Lincoln Murr, Coinbase

Hahnbee Lee of Mintlify and Lincoln Murr of Coinbase discuss what changes when AI agents become the main users of software products. They cover why documentation now needs to be optimized for context windows and accuracy rather than design, how Coinbase is exposing its business through APIs, and how the x402 payment standard and crypto microtransactions let agents pay for services and gain greater autonomy.

Nov 01, 2026

If Your AI Scores 100%, Your Eval Is Wrong - Ramakrishnan Lokanathan, eslams.com

Ramakrishnan Lokanathan argues that AI evals are broken because they are overcomplicated, and lays out a practical framework for building them for high-stakes applications: define the most ambitious version of success, test every step of a workflow, combine automated checks with human review and adversarial tests, guard against regressions, and turn real user failures into tests. He also introduces eSlams, an open-source package where models compete in games like chess, Go, and poker as a window into how they reason.

Technology

View All

Oct 29, 2026

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.

Oct 28, 2026

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.

Oct 28, 2026

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

May 18, 2026

MCP vs ADK: How Modern AI Agents Connect and Work Together

AI agents are having a moment, and understanding MCP and ADK is key to building them well. Cedric Clyburn and Anna Gutowska explain how MCP powers tool integration while ADK structures reliable multi‑agent systems 🤖. Learn when to use each to build more capable and predictable AI agents.

May 17, 2026

Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

A deep dive into AI harnesses, explaining how to build a programmatic environment around an LLM agent to ensure reliability without prompt engineering. The talk demonstrates building a harness for a browser agent to reliably log in and upvote a post on Hacker News using GPT-3.5 Turbo.

May 17, 2026

Fighting AI with AI — Lawrence Jones, Incident

Lawrence Jones from Incident.io explains why their team needed AI to debug their complex AI SRE product. He details three powerful patterns: a CLI for agents to manage large evaluation files, serializing debug UIs into downloadable file systems for agent-based tracing, and multi-agent pipelines for fleet-scale failure analysis.

May 17, 2026

Why Your AI UX Is Broken (and It's Not the Model's Fault) — Mike Christensen, Ably

Mike Christensen from Ably critiques the standard HTTP streaming (SSE) approach for AI chat applications, highlighting its fragility and limitations. He introduces the "durable session" pattern, a persistent, shared resource built on pub/sub principles, to create resilient, multi-device AI experiences with live, bidirectional control.

May 17, 2026

Why AI Agents Break Zero Trust at the Last Mile

AI agents introduce a critical security gap when connecting to legacy enterprise systems, known as the 'agentic last mile identity problem'. This summary explains how losing user identity, context, and delegation breaks zero-trust principles and outlines a solution using a policy-driven vault to manage access and issue short-term credentials.

May 16, 2026

How to Leverage Domain Expertise — Chris Lovejoy, Notius Labs

Chris Lovejoy argues that winning in vertical AI is an organizational challenge, not just a technical one. He introduces a framework of three roles for domain experts—Oracle, Evaluator, and Architect—to effectively embed their knowledge into AI products, illustrated with case studies from companies like Granola and Anterior.

← Previous Next →

Stay In The Loop! Subscribe to Our Newsletter.

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