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

Can you trust your chatbot? Inside three AI-powered cyberattacks

Can you trust your chatbot? Inside three AI-powered cyberattacks

This podcast episode explores three significant AI-enabled cyberattacks: "Dark Sourcery," an AEO poisoning technique that tricks AI chatbots into providing malicious information; an LLM-assisted hacking spree targeting critical vulnerabilities; and an AI agent swarm breaching hundreds of servers with alarming speed. The discussion highlights the evolving threat landscape, the critical importance of cybersecurity hygiene, and the need to rethink trust in AI systems.

AI Can Write the Proof. Who Checks It? — Leonardo de Moura

AI Can Write the Proof. Who Checks It? — Leonardo de Moura

Leonardo de Moura discusses Lean's journey, from its strict "cathedral model" of core development to its current extensibility. He reveals insights from the Collatz exploit, showcasing AI's role in uncovering kernel vulnerabilities and the critical need for robust formal verification. The conversation highlights AI's transformative impact, from generating complex, optimized code (like the zlib proof) to its limitations in true creativity, emphasizing the enduring human responsibility in defining specifications, curating knowledge, and maintaining trust in an AI-assisted future for software and mathematics.

OpenAI DevDay 2026 Keynote (FULL)

OpenAI DevDay 2026 Keynote (FULL)

OpenAI's DevDay unveiled significant advancements including 'Dots' (always-on AI agents for personal and professional delegation), 'ChatGPT Spaces' (a collaborative platform for human-AI teams), and major model updates like GPT-6.1 Sol (cost-effective intelligence) and Astra Ultrafast (unprecedented speed). New developer tools, cloud-based Codex, enhanced APIs, and privacy features were also introduced, alongside strategies for distribution and monetization, underscoring OpenAI's vision of AI as a 'Renaissance' for human empowerment.

What Would Make an AI Assistant Worth Paying For?

What Would Make an AI Assistant Worth Paying For?

This discussion with David Pawlan of Assistant Bench unpacks the explosive growth of personal AI agents, exploring their capabilities, current landscape, and future implications. Topics include diverse agent use cases from daily admin to finance, the evolution of human-agent interfaces (voice, hardware), the critical role of proactivity and trust, the emergence of silent multiplayer agents, and the transformative impact on commerce. The conversation also delves into agent-to-agent interactions, economic models, and the profound shift towards a consumer-aligned internet.

Where AI products go next: voice, agents, and self-driving software | Tara Sesha and Nan Yu (OpenAI)

Where AI products go next: voice, agents, and self-driving software | Tara Sesha and Nan Yu (OpenAI)

A live talk from the Lenny and Friends Summit with OpenAI's Tara Seshan and Nan Yu and host Claire Vo on building AI products when both technology and user expectations change rapidly. Topics include shipping imperfect features (the ChatGPT "toggle"), the 2 to 3 month model-capability horizon, enterprise absorption limits, single versus multi-agent design, platform layering with computer use as a fallback, working with research through evals, direct user relationships, and predictions for voice, proactive agents, and hardware.

The Defender's Window at enterprise scale with Standard Chartered

The Defender's Window at enterprise scale with Standard Chartered

Matt Weaver from OpenAI and Reuben Athaide from Standard Chartered discuss how the bank uses OpenAI Daybreak to address the shrinking "defenders window" by focusing on contextual AI analysis of attack paths, fostering cross-functional trust, and leveraging AI for proactive, scalable security in a complex global environment.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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