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

Why Tejal Patwardhan stopped underestimating the models - Episode 21

Why Tejal Patwardhan stopped underestimating the models - Episode 21

Tejal Patwardhan, head of OpenAI's frontier evals team, discusses the critical evolution of AI evaluations. She explains why traditional benchmarks fail as models become more capable, how OpenAI develops realistic, long-horizon tests (including groundbreaking wet lab experiments), and the implications of rapidly advancing multimodal and reasoning models for scientific discovery and the future of human work.

He's Building an AI That Can't Lie | Dan Klein, Scaled Cognition

He's Building an AI That Can't Lie | Dan Klein, Scaled Cognition

Dan Klein discusses the critical shift in AI from a 'nothing works' to an 'everything works' problem, where fluent LLM outputs often mask deep unreliability. He explores the nature of hallucinations, how reinforcement learning can inadvertently teach deception, and the necessity of building AI systems with inherent metacognition and verifiability. Klein's company, Scaled Cognition, is architecting models where truth and action semantics are first-order design principles, aiming to provide guarantees in a field increasingly dominated by end-to-end optimization.

The State of Frontier Post-Training Recipes | Conversation with Finbarr Timbers

The State of Frontier Post-Training Recipes | Conversation with Finbarr Timbers

This discussion with Finbarr Timbers reviews the evolution of frontier post-training recipes, highlighting the shift from simpler SFT-DPO-RL to complex multi-teacher on-policy distillation (MOPD). It covers the organizational challenges of building models like Olmo, the rise of synthetic data and reasoning-focused RL in DeepSeek, and the complexities of integrating expert teachers, while also exploring open questions on environments, specialized APIs, and career strategies in the rapidly changing AI landscape.

You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia

You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia

Ziv Ilan from NVIDIA details how latency in video diffusion models can be drastically reduced to achieve real-time generation. He presents a layered approach combining dynamic quantization for memory and speed, chunk-based caching to skip redundant denoising computations, and, most critically, step distillation—training models to achieve high-quality output in significantly fewer steps. These techniques, packaged in the open-source FastGen repository, offer additive performance gains, enabling real-time video on a single Blackwell B200 GPU.

Simulating Humans at Scale: Simile's Joon Sung Park

Simulating Humans at Scale: Simile's Joon Sung Park

Joon Sung Park, founder and CEO of Simile and creator of Stanford's "Smallville" generative agents study, explains how Simile is building the "GPU of intelligence" to simulate human society, diverging from frontier models that act as the "CPU of intelligence." He details Simile's approach of grounding simulations with real human behavioral data, its diverse corporate applications, and its long-term vision to create a "CERN of human society" to solve fundamental societal challenges.

Context Engineering for Coding Agents

Context Engineering for Coding Agents

A deep dive into advanced engineering techniques for coding agents, focusing on effective context management in LLMs like Claude. The talk introduces a practical framework using a brain-inspired analogy, proposing a Markdown-based 'wiki' as a long-term memory system to augment the agent's limited context window. This approach is demonstrated through a real-world challenge of extracting structured data from technical drawings.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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