Tokenless

Open Source Security in the Age of AI

Oct 27, 2026

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

Oct 13, 2026

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.

Oct 10, 2026

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.

Oct 10, 2026

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

Oct 27, 2026

We Kept Rebuilding Our AI Agent. Here's What Survived - Fuad Ali, Arize AI

Arize's in-product agent Alex went from a 2023 prototype to a single harness-driven agent with planning, memory, and on-demand skills. AI PM Fuad Ali walks through the decisions behind each change, including moving the plan into the harness, making finish an explicit gate, treating large tool results like files, using one small memory file per user instead of vector stores or knowledge graphs, merging specialists into one agent, and using production sessions as tests.

Oct 27, 2026

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.

Oct 27, 2026

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.

Technology

View All

Oct 28, 2026

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.

Oct 27, 2026

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.

Oct 22, 2026

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.

Recent Post

Oct 05, 2026

The Transcript Looked Fine. The Call Wasn't. — Debugging Voice Agents, Arize

Fuad Ali from Arize AI explains why voice agents are uniquely challenging to debug, as critical issues like latency, interruptions, and tone are invisible in text logs. He presents a solution combining unified audio, transcript, and trace views with OpenInference semantic conventions and audio-native evaluations. The talk culminates in a vision for self-healing voice agents through automated observation, evaluation, and improvement cycles, demonstrating how to achieve robust, continuously improving AI voice systems.

Oct 05, 2026

Evals in AI: A Deep Dive — Tejas Kumar, IBM

This deep dive into AI evaluation (evals) starts by clarifying their role in providing ahead-of-time reliability and security for non-deterministic systems, contrasted with just-in-time harnesses. Tejas Kumar defines evals as "fuzzy unit tests" and outlines their core components: test cases, expected behavior, a judge, and aggregation. He explores various evaluation techniques, emphasizing the challenges and biases of using LLMs as judges, such as position bias, sycophancy, self-preference, and verbosity. The presentation details a practical methodology for calibrating LLM judges against human verdicts using a "golden dataset" to achieve an 80-85% agreement threshold, which can then be enforced as a CI/CD gate. A live coding demonstration illustrates the evolution from simple string matching to a policy-aware LLM judge, showcasing how refining policy and incorporating RAG (Retrieval Augmented Generation) via OpenRAG dramatically improves decision-making. The discussion also covers strategies for maintaining living datasets in production and managing evaluation costs.

Oct 05, 2026

Your AI Agent Is Confidently Wrong About Production — Willem Pienaar, Cleric

Willem Pienaar, CTO of Cleric, details why AI agents struggle with production debugging compared to code generation. He explains the unique challenges of dynamic, unverified production environments and LLMs' inherent confidence bias. Pienaar outlines four common agent failure modes (symptom/cause confusion, missing baselines, abstraction loss, anchoring) and introduces grounding techniques—like generating multiple theories, using baselines and dependency graphs, temporal analysis, and evidence propagation—to enhance diagnostic accuracy. He also emphasizes the critical need for verifying fixes against real outcomes to calibrate agent confidence, ultimately aiming to bring production signals into the development environment for proactive failure prediction.

Oct 05, 2026

Agentic Search vs Vector Search for Coding Agents: We Ran the Eval — Braintrust

This talk by Jess Wang from Braintrust delves into the critical importance of evaluations (evals) in AI development, moving beyond subjective "vibes" to data-driven decision-making. She breaks down the four core components of an eval—dataset, task, scoring, and experiments—and illustrates the continuous improvement "eval flywheel" integrating observability. The central experiment compares agentic search against vector search for a coding agent tasked with finding buggy code in Microsoft's TypeScript Go repo. While both methods achieved identical accuracy, vector search proved four times more expensive due to its inability to capture surrounding context within code chunks, leading to excessive, inefficient searches. Wang concludes with practical caveats and best practices for conducting effective LLM evals.

Oct 05, 2026

How a Logistics Giant Keeps AI Data Locked Down

Jason Ward, FinOps for AI lead at C.H. Robinson, shares insights on managing AI costs for enterprises and startups. He details a FinOps strategy centered on comprehensive tagging, leveraging AI for observability (e.g., detecting prompt bloat and context starvation), and pioneering advanced metrics like "cost per thought" and "reasoning ratio" to optimize complex AI workloads beyond simple discrete tasks.

Oct 05, 2026

Agent Memory Is Solved. Agent Learning Isn't. — Karthik Ranganathan, Yugabyte

Karthik Ranganathan of Yugabyte discusses the critical challenge of shared learning among AI agents, arguing that while per-agent memory is solved, true collective intelligence is not. He details Yugabyte's struggles in building agentic systems, highlighting the "lost context" problem and debunking five common misconceptions about agent memory. Ranganathan introduces Meko, an agent-native persistence layer designed to provide shared, governed, and traceable context through "data packs," drastically improving RAG pipeline faithfulness while reducing context size and token costs. Heather Downing demonstrates Meko's resumability and sharability features, showcasing its ability to foster collaborative learning and capture tribal knowledge across agents.

← Previous Next →

Stay In The Loop! Subscribe to Our Newsletter.

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