Tokenless

Tokenless

Everyone Has the Same AI Models. Here's What Sets Agents Apart - Richmond Alake, Oracle

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
Everyone Has the Same AI Models. Here's What Sets Agents Apart - Richmond Alake, Oracle

Everyone Has the Same AI Models. Here's What Sets Agents Apart - Richmond Alake, Oracle

Richmond Alake argues that after the control plane, agent architectures need an intelligence plane covering what an agent knows, remembers, is allowed to see, and how it improves. He draws on the WWII Midway codebreaking story to separate information from intelligence, then demos a governed agent using an ontology and semantic layer that answers correctly about 99% of the time with far fewer tokens than a naive agent. The talk also covers Oracle's agent memory package, deep data security, private inference, and fine-tuned decision models for memory routing.

Using Agents for Long-Horizon Financial Work — Aman Singh, Arca

Using Agents for Long-Horizon Financial Work — Aman Singh, Arca

Aman Singh, head of AI at Arca, explains how the firm is building an AI-native wealth management business in which agents run back-office work, monitor clients proactively, and coordinate multi-day workflows, while humans retain advisory relationships and trade execution. The discussion covers model selection through internal benchmarks, a model-agnostic custom harness with tiered routing, persistent memory for long-running tasks, deterministic and LLM-based guardrails, auditability by default, decision models for financial accuracy, and feedback loops that turn staff edits into evals.

THE $800B COMPUTE TRAP

THE $800B COMPUTE TRAP

Ben Lorica and Evangelos Simoudis work through Anthropic's S-1 filing, weighing its striking growth and improving unit economics against compute commitments, falling prices from open-weight models, and dependence on coding. They then examine SpaceX's emerging neocloud business and close with a debate over proposed frontier AI regulation, from self-improvement limits to independent testing and incident disclosure.

Technology

View All
Why Founders Are Betting Big on Factories, Mines, and Energy

Why Founders Are Betting Big on Factories, Mines, and Energy

Erin Price-Wright and Connor Love unpack the AD50 and the rebuilding of America's industrial base, covering how defense demand is financing manufacturing capacity for commercial markets, how AI is reshaping factory economics, how a new generation of founders applies lessons from SpaceX, Tesla, Anduril, and Palantir to mining, energy, and manufacturing, and why private capital is now willing to fund physical infrastructure before government demand is guaranteed.

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.

Recent Post

You Can't Prompt the Room: The Last Skill AI Won't Replace - Balázs Horváth, VisualLabs

You Can't Prompt the Room: The Last Skill AI Won't Replace - Balázs Horváth, VisualLabs

AI has shifted the software development bottleneck from coding to defining *what* to build. This talk emphasizes the critical role of human skills in eliciting true requirements and understanding business value, detailing practical tools like story mapping, a 4-question value framework, and the VAD thinking path to ensure valuable AI-driven solutions are built, focusing on impact over mere feature delivery.

Voice In, Visuals Out: The Agony and the Ecstasy - Allen Pike, Forestwalk Labs

Voice In, Visuals Out: The Agony and the Ecstasy - Allen Pike, Forestwalk Labs

Allen Pike (Forestwalk Labs) discusses the power of "voice-in, visuals-out" AI experiences, a paradigm championed by Andrej Karpathy. He highlights the critical challenge of latency in real-time AI interactions and shares three key techniques for achieving low-latency, delightful user experiences: utilizing fast models, employing short inference intervals, and implementing stable caching regimens.

AI-Driven Multi-Document Correlation for Financial Compliance - Varsha Shah, Independent

AI-Driven Multi-Document Correlation for Financial Compliance - Varsha Shah, Independent

Varsha Shah's research introduces an AI-driven framework for enterprise financial compliance and fraud detection, overcoming the limitations of traditional systems that analyze documents in isolation. The framework combines graph-based entity correlation, adaptive probabilistic risk modeling, and cross-jurisdictional normalization to uncover hidden fraud patterns across payroll, tax, procurement, and financial records. Evaluated on 3 million anonymized records across four jurisdictions, it demonstrates significant improvements in detection accuracy (91% precision, 87% recall), reduces false positives by 76%, and lowers manual audit effort by 40%, ultimately transforming compliance from a reactive process into a proactive, intelligence-driven capability through continuous learning.

We Cut 94% of AI Coding Tokens With a Local Code Index - Rajkumar Sakthivel, Tesco

We Cut 94% of AI Coding Tokens With a Local Code Index - Rajkumar Sakthivel, Tesco

Rajkumar Sakthivel details how an unexpected surge in AI coding tool costs led to the discovery that sending excessive, irrelevant context was the primary culprit. He introduces the Code Context Engine (CCE), a local retrieval layer that intelligently prunes context using AST-aware chunks, hybrid search, and relevance scoring, resulting in up to 94% token reduction and significant cost savings. The talk emphasizes that optimizing input context, not just the AI model, is paramount for efficient and accurate AI-assisted coding.

OpenClaw in Your Hand: Building a Physical AI Terminal - Lech Kalinowski, Callstack

OpenClaw in Your Hand: Building a Physical AI Terminal - Lech Kalinowski, Callstack

Dr. Lech Kalinowski presents Vault, a unique AI-native handheld terminal built on an ESP32-S3, featuring a dual-display (OLED for live interaction, e-paper for static content) and powered by a single battery. It operates in four modes—shell, assist, control, and an LLM-native RPG—and controls autonomous OpenClaw agents against a local, self-hosted 120B parameter GPT model served by NVIDIA TensorRT-LLM. The talk delves into the AI-native architecture, why inference remains on the backend, real-time agent thinking surfacing on e-paper, engineering challenges, and LLM-native game design, highlighting the potential for calm, text-first AI interaction.

Research to Reality: Bringing Frontier ML Research to Production - Vaidas Razgaitis, Higharc

Research to Reality: Bringing Frontier ML Research to Production - Vaidas Razgaitis, Higharc

Vaidas Razgaitis, Senior Research Engineer at Higharc, shares three tactical tips to accelerate the transition of novel AI/ML research into production-ready features. He emphasizes addressing the critical handoff challenge between ML researchers and software engineers through structured documentation (Research Prototype Taxonomy Document), a well-organized monorepo utilizing decoupled microservices, and a systematic approach to code decomposition and PR review. These strategies aim to improve legibility, maintainability, and delivery speed for ML-driven products.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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