Tokenless

Tokenless

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

The PHP bug threatening the web. Plus, who's auditing AI?

The PHP bug threatening the web. Plus, who's auditing AI?

Security Intelligence panelists Nick, Don and Jim unpack three stories: two decades-old PHP flaws (PHP2Shell) that let attackers take over servers without logging in and were found by AI before patches landed, Anthropic's decision to give outside evaluators employee-like access and whether rival frontier labs should audit each other, and 333 Tor exit relays hijacked through a reused password. The discussion centers on visibility, patching under legacy constraints, secure by design, and the limits of trust in AI and anonymity networks.

Velocity Through Rigour: Then & Now • Cate Huston • Bug Bash EU 2026

Velocity Through Rigour: Then & Now • Cate Huston • Bug Bash EU 2026

Cate Huston, CTO at Twill and author of The Engineering Leader, shares how she rebuilt a no-code product into a production platform with a two-person team and agents, and argues that the management playbook for scaling people still applies to scaling AI agents. She covers the shift from f(n) to f(n × a) team scaling, the four management layers, guardrails and the roughly 30 percent of output she believes they require, shift-left practices, CI as a cost and quality lever, and why rigour is what turns speed into lasting velocity.

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

Why Education Has to Change

Why Education Has to Change

Ben Horowitz, Erik Torenberg, and Gagan Biyani introduce the Horowitz Andreessen Academy, a new educational model designed for the AI era. They argue that traditional education is ill-suited for a rapidly changing world, advocating for a project-based, "learn by doing" approach. The academy aims to cultivate "main character" builders through immersion in Silicon Valley's culture, strong peer networks, and direct engagement with real-world problems and companies, emphasizing the critical role of people skills and the value of learning from failure in an age where AI empowers unprecedented creation.

Why AI Makes You Worse at the Jobs It Can't Do (with Katie Malone)

Why AI Makes You Worse at the Jobs It Can't Do (with Katie Malone)

Dr. Katie Malone, host of *Linear Digressions*, explains how AI enabled her to relaunch her podcast after a 5.5-year hiatus. She argues that people management and AI agent management are fundamentally the same skill, highlighting the importance of defining tasks, setting acceptance criteria, and 'trust but verify'. Malone discusses the implications of 'AI slop' and 'process slop' in organizations and describes how a "Claude Code in a trench coat" agent now produces her show. She also delves into fascinating data paradoxes, including Bainbridge's Ironies of Automation, Simpsons Paradox, and Benford's Law, emphasizing how human expertise can erode with increasing automation and the counter-intuitive patterns in natural data.

AI Agents Aren't the Revolution. They're the Catalyst!

AI Agents Aren't the Revolution. They're the Catalyst!

Sam Anthony argues that AI agents are not the revolution themselves, but rather a powerful catalyst for profound, lasting changes in the surrounding technology ecosystem. This includes modernizing data infrastructure, standardizing system design, enabling seamless interoperability, democratizing technology and expertise, and shifting human thinking towards outcome-based problem-solving.

When Should AI Systems Use Super Agents?

When Should AI Systems Use Super Agents?

Grant Miller explains the paradox of "super agents" in AI systems – their immense power comes with significant risks. He details concerns like privilege abuse and expanded attack surfaces, contrasting them with the benefits of unified organizational intelligence and workflow coordination. The solution proposed is an architecture of "agent swarms," guided by principles of least agency, isolation, observability, and human oversight, to build secure and scalable agentic systems.

Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip Makraduli

Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip Makraduli

This talk introduces FlashNorm, an optimization for transformer RMS norm layers. It details how algebraic tricks like weight folding, deferred division, and dropped pre-normalization can significantly speed up inference by mitigating GPU inefficiencies. The speaker also shares critical insights from implementing parallel CUDA streams, including debugging a subtle race condition caused by implicit stream joins, and advocates for open inference engines for deploying kernel-level research.

The Frontier AI Inference Cloud for Agents — Byung-Gon (Gon) Chun, FriendliAI

The Frontier AI Inference Cloud for Agents — Byung-Gon (Gon) Chun, FriendliAI

Byung-Gon Chun from FriendliAI details how agentic inference fundamentally differs from traditional chat-based LLM usage, requiring a specialized infrastructure to optimize for end-to-end task completion rather than single request latency. He highlights the economic advantage of open-weight models for agentic workflows and explains FriendliAI's innovative inference stack, featuring prefix caching, advanced KV cache management, cache-aware routing, and agent-aware optimization, which together deliver significant speedups and cost savings for production AI agents.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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