Tokenless

Tokenless

Mark Cuban’s Plan to Make Healthcare Affordable

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
The PHP bug threatening the web. Plus, who's auditing AI?

The PHP bug threatening the web. Plus, who's auditing AI?

Security Intelligence panelists Nick, Don and Jim unpack three stories: two decades-old PHP flaws (PHP2Shell) that let attackers take over servers without logging in and were found by AI before patches landed, Anthropic's decision to give outside evaluators employee-like access and whether rival frontier labs should audit each other, and 333 Tor exit relays hijacked through a reused password. The discussion centers on visibility, patching under legacy constraints, secure by design, and the limits of trust in AI and anonymity networks.

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.

Technology

View All
Mark Cuban’s Plan to Make Healthcare Affordable

Mark Cuban’s Plan to Make Healthcare Affordable

Mark Cuban and Julie Yoo discuss how transparency, direct contracting, and AI could reshape healthcare economics, from Cost Plus Drugs and modular pod manufacturing to personalized medicine, the future of physicians, and advice for founders who want to use AI to learn rather than to stop thinking.

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.

Recent Post

How Software Factories Improve Themselves — Suraj Gupta, Warp

How Software Factories Improve Themselves — Suraj Gupta, Warp

Siraj Gupta of Warp outlines three practical ways software factories can improve over time: self-updating skills driven by outer-loop agents with pull-request review, versioned and traceable persistent memory that works across harnesses, and cost-aware model routing with custom rules and evals.

The grief, loneliness, and burnout sweeping through the tech industry right now

The grief, loneliness, and burnout sweeping through the tech industry right now

Molly Graham revisits her classic "Give Away Your Legos" career advice for an AI era, exploring grief and burnout in tech, the difference between delegating to AI and to humans, the overblown fear of job displacement, which Legos should never be given away, and what effective managers should do now. Key ideas include treating AI as a junior intern, the human sandwich model of vision and review, and reframing careers as evolving rather than disappearing.

AI Is Exposing Your Data: An AI Security Problem You Can't See

AI Is Exposing Your Data: An AI Security Problem You Can't See

Jeff Crume explains how AI agents, RAG pipelines, prompts, tools, and models move sensitive data through modern AI systems, and why traditional DLP falls short. He outlines a unified approach built on data lineage, workload and workforce visibility, proactive risk identification, and compliance reporting.

Can Rewriting an AI Agent Bend the Intelligence Curve? - Zhengyao Jiang

Can Rewriting an AI Agent Bend the Intelligence Curve? - Zhengyao Jiang

Weco let an AI coding agent rewrite the harness around a fixed language model for eight days. Zhengyao Jiang explains what the reported gains show, where the evidence stops short of recursive self-improvement, how reward hacking complicates evaluation, and why human-designed abstractions still anchor the search.

We Let Claude Code and Codex Race Human Researchers — Elie Bakouch, Prime Intellect

We Let Claude Code and Codex Race Human Researchers — Elie Bakouch, Prime Intellect

Elie Bakouch, a research engineer at Prime Intellect, reports on setting Claude Code and Codex loose on the community Optimizer Speedrun, a race to train a GPT-2-level model in the fewest steps. Both agents beat the human record, but they behaved very differently, and none of them invented a new optimizer. The talk closes with a proposed AlphaEvolve-style discovery loop and an argument for doing this research openly.

Beating RL With Reflection: GEPA and Optimize Anything — Lakshya A. Agrawal, GEPA

Beating RL With Reflection: GEPA and Optimize Anything — Lakshya A. Agrawal, GEPA

Lakshya Agrawal, creator of GEPA and a PhD student at UC Berkeley's Sky Computing Lab, presents reflective optimization as an alternative to scalar-reward reinforcement learning. GEPA lets a model read full rollout traces, including reasoning, tool calls, and error messages, and rewrite prompts from that feedback, with a Pareto candidate pool guarding against local optima. The talk covers the GEPA vs. GRPO sample-efficiency comparison, domain-knowledge discovery, the Optimize Anything API for text-based artifacts like code, harnesses, and skills, and production results from Databricks, Snorkel, and others.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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