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

Turn 10,994 Notes Into Memory - Paul Iusztin, Decoding AI & Louis-François Bouchard, Towards AI

Turn 10,994 Notes Into Memory - Paul Iusztin, Decoding AI & Louis-François Bouchard, Towards AI

Paul Iusztin and Louis-Francois Bouchard unveil their AI Research OS, a powerful system that transforms notes, documents, videos, and code repositories into a dynamic, personalized memory for AI agents. They detail a three-layered architecture (raw files, index, wiki) that efficiently manages context and enables continuous learning and evolution, addressing the limitations of static research and generic AI tools.

Full Stack Greenfield Projects : Are they still relevant?

Full Stack Greenfield Projects : Are they still relevant?

Bharat Goenka, co-founder of Tally, discusses the company's unconventional approach to software development through "Full Stack Greenfield" projects. He explains why building every component from scratch, despite being a high-risk strategy, has been crucial for Tally's success in serving the SMB market, fostering extreme customer loyalty, and aspiring to connect 200 million businesses. The talk delves into the historical context, the philosophy of questioning and choosing constraints, and the distinction between product and custom engineering.

The Miranda Hypothesis: How Hamilton Poisoned Persona Evals - Jacob E. Thomas, Results Gen

The Miranda Hypothesis: How Hamilton Poisoned Persona Evals - Jacob E. Thomas, Results Gen

This talk exposes "Miranda distortion," a critical flaw in AI personas where models, influenced by modern cultural narratives, produce convincing but anachronistic outputs. Current evaluations fail to detect this, prioritizing fluency over fidelity. The speaker proposes "epistemic simulation"—a new paradigm grounded in corpus-bounded, temporally-anchored, and expert-evaluated reasoning—and introduces the "Prism Experiment." This rigorous, pre-registered protocol uses Abraham Lincoln to demonstrate how a weighted rubric, created by historians and de-emphasizing rhetorical fluency, can detect anachronism. It advocates for the "humanist in the loop" as a technical requirement to ensure AI personas are true to their documentary records, not just convincing.

Zynga Founder: Consumer Is Not Investible Right Now - Thats Why You Should Build It

Zynga Founder: Consumer Is Not Investible Right Now - Thats Why You Should Build It

Mark Pincus, founder of Zynga, discusses the product philosophy behind "Life at the Speed of Play," focusing on consumer innovation in the AI age. He introduces the "Proven, Better, New" framework, shares insights on founder mode, and predicts a future where "intelligence on tap" driven by free AI compute will unlock unprecedented opportunities for new "internet treasures," despite current investor skepticism in the consumer space.

Memory and Continual Learning: Engram's Dan Biderman and Jessy Lin

Memory and Continual Learning: Engram's Dan Biderman and Jessy Lin

Dan Biderman and Jessy Lin of Engram introduce their "always training" paradigm, focusing on baking a team's knowledge directly into a model's weights to achieve true memory and continual learning. This contrarian approach, which they call a "RAG killer" for specific use cases, promises up to 100x token savings and superior performance by internalizing context rather than relying on ever-larger context windows or external retrieval, envisioning a future where everyone has their own continually learning, personalized AI model.

The Evolution of User Interfaces • Ken Pfeuffer • GOTO 2025

The Evolution of User Interfaces • Ken Pfeuffer • GOTO 2025

Ken Pfeuffer discusses the evolution of user interfaces, from traditional hand-centric inputs to the emerging paradigm of eye-hand symbiosis. He traces the history of gaze interaction research, explains his decade-long work on "gaze and pinch," and shares how these concepts are now becoming reality with devices like Apple Vision Pro, outlining future directions for intuitive spatial computing.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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