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

The Future of Frontier Model Architectures with Walter Goodwin, Founder & CEO of Fractile

The Future of Frontier Model Architectures with Walter Goodwin, Founder & CEO of Fractile

Walter Goodwin, founder and CEO of full-stack AI chip company Fractile, discusses the bets behind his company's inference chips, including memory bandwidth as the key constraint, the value of owning the entire chip stack, compressing the gap between chip design and deployment, and how the accelerator market may evolve as frontier labs pursue faster inference.

OpenAI cancels Astra release, Sonnet 5.5 & what Meta Muse means for work

OpenAI cancels Astra release, Sonnet 5.5 & what Meta Muse means for work

IBM's Mixture of Experts panel examines OpenAI's decision to withhold GPT-6.1 Astra, Anthropic's Sonnet 5.5 blurring the line between mid-tier and top-tier models, and Meta's Muse agent as a bridge between consumer AI habits and enterprise expectations, with a detour into token budgets, model routing, and AI governance.

Stop Renting Your AI's Memory — Dylan Couzon, Qdrant

Stop Renting Your AI's Memory — Dylan Couzon, Qdrant

Dylan Couzon, developer relations engineer at Qdrant, argues that frontier-class models now run on hardware people can own, but the memory that makes an assistant personal still lives in someone else's cloud. He covers why owning inference gives autonomy while owning memory gives continuity, the CPU, RAM, and disk model for LLMs, why retrieval beats stuffing everything into the prompt, and a live offline demo of a drone building searchable memory with Qdrant Edge, plus opt-in shared memory.

How a Voice Agent Learns the Rhythm of Conversation — Shawn Wen

How a Voice Agent Learns the Rhythm of Conversation — Shawn Wen

Shawn, CTO of PolyAI, explains why voice agents are harder than text agents: voice adds time, and good conversation depends on adapting to the person on the line. He describes Dialog-RSN-1, an audio-native model that predicts turn-taking, replies in text with citations, and writes the transcript last for auditability, along with training on real noisy calls, latency and what agents should do while thinking, voice personality, benchmarking, harness ownership, and the shifting bottleneck from producing content to validating it.

From deepfakes to DNA: the science of watermarking AI

From deepfakes to DNA: the science of watermarking AI

Hannah Fry talks with Pushmeet Kohli and Jeremy Ratcliffe about SynthID, DeepMind's invisible watermarking technology. They cover its origins and design requirements, how it works for text, images, and video, why it matters for regulation and misinformation, and how SynthID Bio extends watermarking to protein structures and sequences to help screen AI-designed biological material without changing function.

Why One Internet Pioneer Thinks the Original Model Broke

Why One Internet Pioneer Thinks the Original Model Broke

Barrett Lyon, founder of DoxxNet, explains why he believes the internet's protocols are due for another wave of experimentation and why traditional VPNs only address part of the privacy problem. He describes a mesh network where users communicate peer-to-peer without central servers, the company's owned infrastructure and locally run AI, and the growing threat of ad tracking combined with AI aggregation. The conversation also covers lessons from DDoS defense, internet mapping, and a career spanning networking and art.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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