Tokenless

Tokenless

Open Source Security in the Age of AI

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
Stop Giving Your Agent Tools. Give It a Sandbox - Mikyo King, Arize AI

Stop Giving Your Agent Tools. Give It a Sandbox - Mikyo King, Arize AI

Mikyo King, head of open source at Arize AI, explains code mode, an agent architecture where the model searches for tools and composes them in a sandboxed programming environment instead of loading large tool catalogs into context. He covers why it works, how Arize built it into Phoenix with Bash, Python, SQL, and UI control, its hidden costs around secrets, permissions, durability, and double sandboxing, and Harbor evals showing 43% fewer tokens and 31% lower cost.

What a $900M Bank Error Teaches Us About AI Agents - John Feminella, Two Sigma

What a $900M Bank Error Teaches Us About AI Agents - John Feminella, Two Sigma

John Feminella of Two Sigma uses a 2020 Citibank payment error to show how AI agents can be given real autonomy through five composable controls: an agent registry, risk-based review, purpose-scoped tool access, shared evals, and classifiers that send humans only the approvals that matter.

The AI School Kids Love More Than Vacation | Alpha School's Joe Liemandt

The AI School Kids Love More Than Vacation | Alpha School's Joe Liemandt

Alpha School principal Joe Liemandt and Horowitz Andreessen Academy co-founder Gagan Biyani discuss how AI-powered learning could compress core academics into two hours a day, freeing the rest of school for teamwork, entrepreneurship, and real-world building, and what that model means for K-12 families, higher education, and the next generation of builders.

Technology

View All
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.

What will computer chips look like in 2045?

What will computer chips look like in 2045?

Intel's leadership walks through how advanced process nodes are brought to volume, from yield learning and the lessons of 10nm to the shift from planar transistors to gate-all-around, High-NA EUV, backside power, and CFET. The discussion widens to the chip-to-chip bottleneck that hybrid bonding targets, the supply limits on EUV tooling as AI compute demand grows, and the economics that make foundry scale decisive.

Former Intel CEO: Why This is the Best Time to Build Hardware

Former Intel CEO: Why This is the Best Time to Build Hardware

Pat Gelsinger joins a16z's Raghu Raghuram and Guido Appenzeller to discuss how AI is reshaping chip design, why design speed alone will not fix semiconductor bottlenecks, and why power and energy capacity may ultimately limit AI growth. The conversation covers HBM and memory innovation, stacking limits, the shift from copper to optics, consolidation among AI chip startups, and what a VMware for AI agents might look like.

Recent Post

Beam: The Great American Open Model with ReflectionAI Co-Founder and CEO Misha Laskin

Beam: The Great American Open Model with ReflectionAI Co-Founder and CEO Misha Laskin

Misha Laskin, co-founder and CEO of Reflection AI, discusses the company's 500B open-weight reasoning model Beam, the economics of frontier training, the shift from renting to owning intelligence in enterprise, the role of Chinese open models in the global ecosystem, and the case that openness itself is a safety strategy. He also reflects on how AI is accelerating scientific research and reshaping research team sizes.

OpenAI's always-on agents, 700+ math manuscripts & HackerRank's AI interviewer

OpenAI's always-on agents, 700+ math manuscripts & HackerRank's AI interviewer

The panel covers OpenAI's Dots and the wave of persistent AI agents, OpenAI's release of hundreds of AI-generated math manuscripts and what it means for human mathematicians, and HackerRank's Chakra AI interviewer and its implications for fairness and evaluation. The episode closes with an explainer on mixture of experts architectures and the difference between open-weight and open-source models.

Data pipeline at Petabyte scale: Production Video Curation with Ray on CoreWeave

Data pipeline at Petabyte scale: Production Video Curation with Ray on CoreWeave

A walkthrough of how Anyscale and CoreWeave scaled a video captioning pipeline from 600 GB to about 6 PB, running managed Ray on CoreWeave Kubernetes Service with CAIOS caching. The talk covers the stack, the bottlenecks that drove GPU utilization from about 10% to near 100%, storage and fault-tolerance design, and the throughput achieved across 1,500 or more GPUs.

Quota Isn't Enough: Topology Aware Scheduling on Modern GPU Clusters

Quota Isn't Enough: Topology Aware Scheduling on Modern GPU Clusters

A deep dive into why rack-scale NVL72 GPU hardware makes topology a scheduling requirement, and how Kueue's Topology Aware Scheduling (TAS) brings NVLink domains, rack boundaries, and PodSet slices into Kubernetes admission. Covers preferred vs. required placement, the performance cliff between NVLink and InfiniBand, and production lessons on sticky scheduling, quota debugging, fragmentation, node hot swaps, and the upstream path toward configurable preemption.

AI Writes More PRs. Who Validates Them? — Ali-Reza Adl-Tabatabai, Sonar

AI Writes More PRs. Who Validates Them? — Ali-Reza Adl-Tabatabai, Sonar

Ali-Reza Adl-Tabatabai, co-founder of Gitar (now part of Sonar), explains why AI-driven growth in PR volume and size turns CI and code review into a bottleneck, and presents agentic validation as the way out: automated review, CI failure analysis, autofix, and auto-merge, built up step by step as trust grows, combined with traditional program analysis in SonarQube.

Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab

Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab

Felipe Blanes from the Amazon AGI Lab shares lessons from working directly with customers of Nova Act, Amazon's browser agent service, from research preview to general availability on AWS. He argues that static benchmarks leave teams hoping their evals match real usage, and proposes a customer-driven eval flywheel, the trust cliff around 90% reliability, the value of being open about limits, and principles for keeping evals fresh.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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