Tokenless

Tokenless

How Anthropic Merges 30,000 Code Changes a Day - Manish Kapur, Sonar & Addy Osmani, Anthropic

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 a One-Line Change Can Break Your Whole Stack - Cole Gannaway, Qodo

Why a One-Line Change Can Break Your Whole Stack - Cole Gannaway, Qodo

placeholder

How Anthropic Merges 30,000 Code Changes a Day - Manish Kapur, Sonar & Addy Osmani, Anthropic

How Anthropic Merges 30,000 Code Changes a Day - Manish Kapur, Sonar & Addy Osmani, Anthropic

Manish Kapur of Sonar and Addy Osmani of Anthropic discuss why coding agents are opening pull requests faster than teams can review them, how light and dark software factories differ, how Anthropic scaled to around 30,000 merged changes a day with Claude doing first-pass review backed by verification evidence, new State of Code survey data, and why every loop in the factory needs independent, multi-layered verification.

AI That Hunts Logic Bugs Before Attackers Do - Taylor Luttrell-Williams, Sonar

AI That Hunts Logic Bugs Before Attackers Do - Taylor Luttrell-Williams, Sonar

Sonar's Taylor Luttrell-Williams introduces SonarQube Hunter Agent, an AI security agent that finds intent-level flaws such as broken access control, business logic gaps, and authentication holes that pattern-based SAST cannot detect. The talk covers its multi-agent pipeline with adversarial validation, Sonar's join to the OpenAI Daybreak Cyber Partner Program, and a live demo that surfaced 46 issues in a Python app, including a self-promotion to admin and an MFA bypass.

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

The Inference Frontier: from 100 to 10,000 tokens per second — Sean Lie, Cerebras CTO

The Inference Frontier: from 100 to 10,000 tokens per second — Sean Lie, Cerebras CTO

Cerebras CTO Sean Lie discusses the

AI agents for therapeutic reasoning across biological contexts

AI agents for therapeutic reasoning across biological contexts

Medea is an AI agent for therapeutic reasoning designed to overcome limitations of existing AI in preserving biological context, verifying computational steps, and reconciling conflicting evidence. It employs a modular architecture with robust verification mechanisms for research planning, analysis, literature reasoning, and multi-round discussion, demonstrating superior performance in cell type-specific target nomination, synthetic lethality prediction, and immunotherapy response prediction across various biological contexts and data types.

Inside Moderna’s Biggest mRNA Test Since COVID

Inside Moderna’s Biggest mRNA Test Since COVID

Moderna CEO Stéphane Bancel discusses the groundbreaking positive Phase 3 results for their individualized mRNA cancer vaccine combined with Keytruda for melanoma. He explains the personalized approach of sequencing patient tumors to teach the immune system specific cancer signatures, the engineering challenges of manufacturing a unique medicine for every patient, and Moderna's ambitious plans to expand this technology beyond melanoma to other cancers, rare genetic diseases, and autoimmune conditions.

Why OpenAI is calling for a ‘cyber defense surge.’ Plus: Find Evil! winners and TeamPCP losers

Why OpenAI is calling for a ‘cyber defense surge.’ Plus: Find Evil! winners and TeamPCP losers

IBM and OpenAI, alongside 100+ organizations, have called for a 'global surge in cyber defense' to counter escalating AI-enabled attacks, emphasizing collective action and proactive remediation strategies over mere threat intelligence sharing. Concurrently, the SANS Institute's 'Find Evil!' hackathon revealed autonomous AI agents capable of advanced cyber investigation, though human oversight remains crucial for incident response actions due to AI's limitations. The podcast also dissects the unmasking of the TeamPCP hacking group, highlighting how basic cybersecurity hygiene failures led to their downfall, underscoring that even sophisticated threat actors are susceptible to fundamental operational security lapses.

Agent Spending Without Controls — Rodrigo Coelho & Pranav Maheshwari, Edge & Node

Agent Spending Without Controls — Rodrigo Coelho & Pranav Maheshwari, Edge & Node

Ampersand presents the critical need for a new payment infrastructure for AI agents, moving beyond traditional human-centric rails to address machine-speed transactions and stringent enterprise compliance requirements. The presentation highlights how agents require access to paid tools via a "skill file" and demonstrates agentic e-commerce, culminating in a crucial demo of real-time sanctions screening for wallet addresses.

Building AI That Optimizes AI

Building AI That Optimizes AI

Wafer (S24) is a fast AI inference cloud that runs open-source models at industry-leading speeds by using AI agents to optimize GPUs across the entire stack. This unique approach allows them to deliver the low cost of open source with the latency of much smaller models. The company recently raised a $40 million Series A after achieving rapid growth by making GLM 5.2 run 2-3x faster than competitors, driving significant customer adoption due to speed, not just cost, which is crucial for latency-sensitive applications like voice agents.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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