Tokenless

Tokenless

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

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

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.

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.

Technology

View All
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.

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.

Recent Post

AI, Infrastructure, and the Next Investment Cycle

AI, Infrastructure, and the Next Investment Cycle

David George, Sarah Wang, Alex Immerman, and Santiago Rodriguez from a16z walk through 25 charts from their State of Markets presentation, covering why markets are rising on earnings rather than multiple expansion, the roughly $780B hyperscaler capex race, the new age of atoms in physical infrastructure, enterprise AI adoption gaps, agent economics and falling inference costs, consumer AI and marketplace disruption, the bifurcation of SaaS, the rise of mega private companies, and the sectors they are most excited about next.

The State of AI in Software Development: Data from 400+ Orgs — Justin Reock, DX

The State of AI in Software Development: Data from 400+ Orgs — Justin Reock, DX

Justin Reock of DX presents five trends from research on about 200,000 engineers, covering deployment frequency, change failure rate volatility, the maintainability and change confidence gap, growing PR sizes, differences across junior and senior engineers, the DX AI Measurement Framework, platform AI readiness, agent experience, and why code generation was never the bottleneck. Case studies from Morgan Stanley, Zapier, and Spotify illustrate AI applied across the SDLC.

The Chief AI Officer: Scientist, Architect, Coach — Rania Khalaf, WSO2

The Chief AI Officer: Scientist, Architect, Coach — Rania Khalaf, WSO2

Rania Khalaf, Chief AI Officer at WSO2 and formerly a long-time leader at IBM Research, shares a framework for a role that is still being defined. She covers the Scientist, Architect and Coach focus areas, how the balance shifts by company type and AI maturity, and why she measures AI adoption, agent readiness and market signals instead of token counts. She also addresses the need for CEO backing and the question of who should own AI.

The Death of the Code Review: What the Data Actually Says — Laurie Voss, Arize AI

The Death of the Code Review: What the Data Actually Says — Laurie Voss, Arize AI

Agents have multiplied code output, but human review cannot keep pace, and reviewer effectiveness collapses past roughly 400 lines. This talk by Laurie Voss surveys what OpenAI, METR, Cognition, Cursor, GitHub, Carlini, and Bun are doing about it, from mergeability benchmarks and multipass automated review to prompt injection and production monitoring as the last line of defense.

Your Agents Are in Solitary Confinement: Why MCP & A2A Aren't Enough — Vlad Luzin, Band

Your Agents Are in Solitary Confinement: Why MCP & A2A Aren't Enough — Vlad Luzin, Band

Vlad Luzin, co-founder and CTO of Band, argues that connecting AI agents is a distributed systems problem that current tools such as MCP, A2A and messaging platforms do not solve. He lays out what is required for real agent collaboration, including ordered real-time transport, persistence, runtime binding, agent-first abstractions and governance, then demonstrates Codex, LangGraph and Claude Code agents finding and working with each other under full human-in-the-loop visibility.

AslanX Flow in Action: Training & Deploying a CFD Surrogate Model | Deep Dive — Mason Seo

AslanX Flow in Action: Training & Deploying a CFD Surrogate Model | Deep Dive — Mason Seo

Mason Seo, CTO of Narnia Labs, demonstrates AslanX Flow, a platform enabling engineers to train, evaluate, and deploy surrogate models for 3D field prediction (e.g., CFD aerodynamics) without a dedicated machine learning engineer. The deep dive covers building a training workflow from raw engineering data, comparing model architectures like PointNet, Transolver, and Linear Neural Operator, and deploying the winning model as a no-code inference application. A key insight shared is the importance of evaluating models on specific engineering data, as public leaderboard performance doesn't always translate, alongside a preview of AI-driven workflow configuration.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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