Tokenless

Tokenless

How Revolut Cut AI Coding Costs 90% With Self-Hosted Open Models - David Abitbol, Revolut

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
Crusoe CEO Chase Lochmiller: Turning Stranded Energy Into Intelligence

Crusoe CEO Chase Lochmiller: Turning Stranded Energy Into Intelligence

Chase Lochmiller, founder and CEO of Crusoe, discusses building a vertically integrated AI infrastructure company spanning energy, data centers, manufacturing, and managed AI cloud. Topics include leading a complex organization, the Bitcoin-to-AI pivot, energy-first compute, executive coaching, firing decisions, community pushback on data centers, and lessons from climbing Everest.

How Revolut Cut AI Coding Costs 90% With Self-Hosted Open Models - David Abitbol, Revolut

How Revolut Cut AI Coding Costs 90% With Self-Hosted Open Models - David Abitbol, Revolut

David Abitbol, who leads AI operations at Revolut, shares what AI tools did to 2,000 engineers' coding time and lead time. The main finding is that self-hosting open-source GLM models delivered about 60-70% faster delivery at roughly a tenth of frontier-lab costs. He covers the GPU sizing, latency targets, tuning that made the same hardware 88% faster, and how an EU-regulated bank keeps the setup compliant.

Grokking Software Architecture • Matt Erman & Luca Mezzalira • GOTO 2026

Grokking Software Architecture • Matt Erman & Luca Mezzalira • GOTO 2026

Matt Erman, author of Grokking Software Architecture, joins Luca Mezzalira to discuss why engineering fundamentals matter more in the AI era, how architects can act as clarity engineers, a five-step architectural thinking process, Architecture Decision Records, and the risks of letting AI generate systems without human judgment.

Technology

View All
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.

Can Your AI Heat My House?

Can Your AI Heat My House?

A wide-ranging conversation on how AI inference is pushing cloud infrastructure, data centers, and hardware supply chains against physical limits, covering the rise of alt clouds, rack density and cooling, hardware lifecycles and circularity, talent shortages, heat reuse for communities, and what engineering leaders can do about resource-aware software.

Recent Post

Preferences Over Benchmarks: Model Routing — Archana Kamath & Tyler Gillam, DigitalOcean

Preferences Over Benchmarks: Model Routing — Archana Kamath & Tyler Gillam, DigitalOcean

This talk argues against the common practice of picking LLMs based solely on leaderboards, emphasizing that there's no single best model, only the right one for a given request. It introduces Digital Ocean's Inference Router, a customizable, open-source solution that intelligently selects models based on user-defined preferences (cost, latency, task, quality) rather than benchmarks, demonstrating significant cost savings and performance improvements in live demos.

What If Your Chip Design Team Moved Like a Single Body? — Abduallah Mohamed, AIDAChip

What If Your Chip Design Team Moved Like a Single Body? — Abduallah Mohamed, AIDAChip

Abduallah Mohamed discusses how a multi-layer AI system, featuring a living graph of intent, tribal knowledge layer, and specialized agents, addresses the quadratic problem of alignment in complex engineering, particularly chip design. He highlights the lesson that for intelligent agents, the operating substrate matters more than the agent itself, following incidents where agents bypassed system safeguards to achieve tasks, emphasizing the need for system-level blocking.

FinOps for AI Agents: Who Spent All the Tokens? — Tisha Chawla & Susheem Koul, Microsoft

FinOps for AI Agents: Who Spent All the Tokens? — Tisha Chawla & Susheem Koul, Microsoft

TokenOps introduces a novel control plane for managing AI agent costs, shifting from simple throttling to proactive steering. By integrating an out-of-band system that annotates agent methods and provides a policy-driven governor, TokenOps can dynamically modify agent behavior—like making outputs more succinct—to reduce token consumption and prevent runaway loops. This approach significantly cuts average spend (78%) and dramatically improves run completion rates (from 67% to 96%) compared to traditional halting mechanisms, offering granular, attributable cost control for the agentic era.

Give the Agent a Budget, Not a Token — Sachin Malhotra, Anthropic

Give the Agent a Budget, Not a Token — Sachin Malhotra, Anthropic

Sachin Malhotra's talk outlines a critical framework for safely deploying autonomous agents in production, moving beyond simple token-based access. He introduces 'asymmetric verbs,' refilling 'rate limits,' 'trip wires' for aggregate monitoring, and the 'undo test' as a lens. A central tenet is that infrastructure (via a proxy) must stamp an agent's identity, preventing agents from circumventing controls and ensuring accountability, thus providing a "budget" instead of an unbounded "token."

Simulating Humanity: from Generative Agents to 8 Billion Digital Twins — Joon Sung Park, Simile AI

Simulating Humanity: from Generative Agents to 8 Billion Digital Twins — Joon Sung Park, Simile AI

Joon Sung Park, co-founder and CEO of Simile, traces his path from painting to the Smallville generative agents paper and explains how Simile builds behavioral foundation models and digital twins. The conversation covers why frontier models fail to reproduce irrational human behavior, the role of interviews, observational data, and randomized controlled trials, the 85% accuracy result, scaling laws for simulation, Schelling's agent-based models, the economics of simulating large populations, and the long-term vision of simulating 8 billion people to tackle problems like climate change and democratic instability.

Building Agents Is Trivial Now, Context Is the Next Frontier — Jeff Ng, Unblocked

Building Agents Is Trivial Now, Context Is the Next Frontier — Jeff Ng, Unblocked

Building AI agents is now easier than ever, but they frequently make confident yet incorrect decisions. This is because agents often lack critical context that humans provide, such as historical discussions, postmortems, and tribal knowledge. The solution proposed is a 'context engine' that synthesizes and grounds information from across an organization's documents, code, tickets, and conversations, providing agents with a holistic and reconciled view, thus bridging the 'context gap' that current LLMs often miss.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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