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

Build a Research Agent with Claude Managed Agents (Part 2 of 4) — Anthropic

Build a Research Agent with Claude Managed Agents (Part 2 of 4) — Anthropic

A hands-on walkthrough of Claude Managed Agents, building a research desk for SEC filing analysis with a chat UI on the session event stream, skills, subagents, custom tools, shared memory, rubric-graded outcomes and vault-based credential injection.

Claude Managed Agents Q&A: Evals, CI/CD and Multi-Tenancy (Part 4 of 4) — Anthropic

Claude Managed Agents Q&A: Evals, CI/CD and Multi-Tenancy (Part 4 of 4) — Anthropic

A Q&A from the final part of Anthropic's Claude Managed Agents workshop, covering CI/CD for agent configs in YAML with the ant CLI, eval practices, workspace-based resource sharing and tenant isolation, agent-driven code review, GPU-enabled self-hosted sandboxes, multiplayer Slack agents, long-running sessions, and the coordinator pattern for custom tools.

The Next Trillion Internet Users Still Don’t Have an Identity — Adi Singh, AgentMail

The Next Trillion Internet Users Still Don’t Have an Identity — Adi Singh, AgentMail

Adi Singh, co-founder of AgentMail, argues that agent identity will accumulate on surfaces humans already use, like email, rather than being issued through a new spec. He draws on an experiment where an unsupervised agent recruited other agents, the way MCP spread by bringing tools into existing apps, and a real autonomous signup flow with Telnyx. He also examines why these surfaces are both a trust layer and an attack surface.

AI Security Engineer Foundations + Certificate — Javier Garza, Snyk

AI Security Engineer Foundations + Certificate — Javier Garza, Snyk

Javier Garza's AI Security Engineer Foundations workshop walks through the OWASP LLM Top 10, shadow AI and AI Bills of Materials, AI threat modeling, securing agent skills and MCP servers, secure vibe coding, and offensive agent workflows. Throughout, he argues that AI systems break traditional security assumptions because they are probabilistic, reach external content, and act through tools, so defenses must combine least-privilege access, continuous inventory, automated scanning, human approval, and education that explains guardrails rather than merely imposing them.

SonarQube + OpenAI: Agentic Development — Killian Carlsen-Phelan, Sonar

SonarQube + OpenAI: Agentic Development — Killian Carlsen-Phelan, Sonar

A hands-on look at pairing Codex with SonarQube to verify agent-generated code inside the coding loop. The walkthrough covers secrets blocking, SQL injection remediation with a parameterized query, real-time agentic analysis, and the argument that completion requires evidence, containment is not correctness, and feedback belongs inside the agent loop.

Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI

Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI

A financial agent produces confident investment advice with fabricated details, redundant tool calls and bad summaries. This talk shows how traces, evaluations, and a coding agent connected through the Arize CLI and skills can investigate those failures, propose fixes, and test them with experiments. It covers why evaluations matter over vibes-based shipping, how judges and costs fit in, and why human review and application-specific evals are still essential.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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