Tokenless

Tokenless

Why Humans Can't Keep Up With AI-Written Code - Tariq Shaukat, 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
Why Humans Can't Keep Up With AI-Written Code - Tariq Shaukat, Sonar

Why Humans Can't Keep Up With AI-Written Code - Tariq Shaukat, Sonar

Sonar CEO Tariq Shaukat argues that agents have made code abundant but confidence scarce, and draws on Toyota's quality-first factory principles to show how to build software factories enterprises can trust. He covers five hard problems that break agentic development and presents Sonar's code confidence formula: intent, guide rails, verification, and evidence.

From AI Slop to Software Factories ft. Dexter Horthy

From AI Slop to Software Factories ft. Dexter Horthy

A tandem bike ride through Amsterdam turns into a wide-ranging conversation with Dexter Horthy, co-founder of HumanLayer, on code no one understands, computer use, MCP design, browser agents, chat interfaces, and the infrastructure every team needs for agent-based software factories.

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.

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

The Reason Your Claude Output Still Looks Like Slop (with Priyanka Vergadia)

The Reason Your Claude Output Still Looks Like Slop (with Priyanka Vergadia)

Priyanka Vergadia, The Cloud Girl, discusses why most companies see no ROI from AI tools, proposing a 7:1 budget split for training over tools. She explains how AI has made "taste" the new ceiling, detailing how to build effective Claude skills by breaking tasks into explicit subtasks with human-in-the-loop oversight. She introduces her 10-20-70 framework for AI budgets, emphasizing the long-term investment needed for employee skilling and community building. Priyanka also shares her transition to full-time entrepreneurship, focusing on product and career storytelling, and reveals her upcoming book on tech storytelling.

MCP Goes Stateless | ​John Dellenbaugh & Pankaj Kumar | MCP Release Party - Seattle

MCP Goes Stateless | ​John Dellenbaugh & Pankaj Kumar | MCP Release Party - Seattle

This session details the transformation of the MCP protocol to a stateless design, addressing previous scaling challenges by externalizing session state to a database and eliminating the need for sticky sessions and complex infrastructure. The presentation includes a live demo comparing stateful and stateless architectures, highlighting benefits in scalability and simplified deployment. It also covers considerations for security and data resiliency within this new paradigm.

Policy Enforcement and Tamper-Evident Audit Chains | ​Imran Siddique | MCP Release Party - Seattle

Policy Enforcement and Tamper-Evident Audit Chains | ​Imran Siddique | MCP Release Party - Seattle

Imran Siddique introduces cMCP, an open-source gateway that enhances Modular Control Plane (MCP) servers with policy enforcement and tamper-evident audit trails. It achieves this by running Cedar policy evaluation within Trusted Execution Environments (TEEs), ensuring that agent actions are governed securely and verifiably. The talk delves into the concept of "beyond governance" towards verifiable AI, the 'trace' standard for auditable logging, and the importance of confidential computing for regulated industries.

How to Kill the Code Review — Ankit Jain, Aviator

How to Kill the Code Review — Ankit Jain, Aviator

Ankit Jain argues that traditional line-by-line code review is defunct, with AI reviewing code that humans no longer read. He asserts that code review's vital, often overlooked, purpose is 'alignment'—knowledge sharing, mentorship, and architectural feedback—which current AI-driven workflows fail to capture. His proposal involves capturing user-AI interaction prompts as acceptance criteria, generating test plans with an 'AI Slop Registry' (codified recurring review comments), and verifying changes against live previews. The new review surface becomes the 'intent and evidence' rather than the code diff, preserving collaboration and ensuring semantic accuracy.

Security Firewall for Agents — Ryan Dahl, Deno

Security Firewall for Agents — Ryan Dahl, Deno

Deno addresses the critical security challenge of AI agents with production write access by introducing Claw Patrol. This MIT-licensed proxy operates below the HTTP layer, deep inspecting all agent communications (including non-HTTP protocols), enforcing granular HCL-based rules, and handling credential injection. It allows for human or LLM approval workflows, ensuring robust, external security against prompt injection and malicious actions, as agents are fundamentally considered untrusted software.

Context Engineering in 2026 — Louis-François Bouchard, Omar Solano & Samridhi Vaid, Towards AI

Context Engineering in 2026 — Louis-François Bouchard, Omar Solano & Samridhi Vaid, Towards AI

Experiments with an AI tutor reveal that not compacting context often outperforms summarization, leading to better recall, lower cost, and faster responses, primarily due to LLM API prompt caching. Compaction invalidates the cache, making it unexpectedly expensive. While cloud environments benefit from full history, local hardware limits necessitate compaction, highlighting the need to prioritize actual constraints over default compaction strategies.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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