Tokenless

Tokenless

GPT-5.6 Sol, FIFA AI & Wall Street’s AI nerves

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
Frontier results, on device - RL Nabors, Arize

Frontier results, on device - RL Nabors, Arize

RL Nabors discusses the significant costs associated with using frontier AI models, covering security, latency, and financial implications. She introduces a framework for right-sizing AI solutions by leveraging smaller, task-specific models and Small Language Models (SLMs). The framework details how to prove task feasibility, establish success criteria with golden datasets, conduct capability evaluations (using tools like Phoenix), and select the most appropriate "Small And Good Enough" (SAGE) model. Nabors further demonstrates how prompt engineering, particularly few-shot prompting, and post-processing can close performance gaps with larger models, while advocating for continuous regression evaluations to maintain performance integrity. The overarching message is to "prototype big, deploy small" to optimize AI deployments.

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.

Uncertainty-Guided Data Augmentation for Engineers | Deep Dive - Yongmin Kwon

Uncertainty-Guided Data Augmentation for Engineers | Deep Dive - Yongmin Kwon

This session details a data-efficient method for training engineering surrogate models by using uncertainty quantification (UQ) to guide geometric data augmentation. Instead of random deformations, the approach lets the deep ensemble model identify its own knowledge gaps (epistemic uncertainty), then uses Free-Form Deformation (FFD) to generate new shapes specifically in those uncertain regions. This ensures every expensive simulation run yields maximally informative data, significantly improving model accuracy for a fixed computational budget across domains like structural mechanics and aerodynamics.

Artificial Intelligence

View All
GPT-5.6 Sol, FIFA AI & Wall Street’s AI nerves

GPT-5.6 Sol, FIFA AI & Wall Street’s AI nerves

OpenAI's new GPT-5.6 Sol model sparks debate on AI safety and release strategies, while Wall Street expresses growing skepticism over the long-term economics of frontier AI models. The discussion also touches on AI's impact on the FIFA World Cup and a thought-provoking paper comparing LLM anthropomorphism to Age of Empires II "goats."

The Prompt Is Still a Punch Card - Ted Johnson, JoinIn AI

The Prompt Is Still a Punch Card - Ted Johnson, JoinIn AI

Ted Johnson argues that current AI interfaces, particularly prompting, operate on an outdated "batch processing" protocol akin to punch cards. Despite advanced LLM capabilities, this interface design forces humans to adapt to machines, hindering natural interaction. He advocates for a shift towards human-compatible interfaces where AI actively participates in real-time conversation, leveraging its intelligence to remove user burdens and amplify human potential.

How Nuclear Will Unlock Energy Abundance with Valar Atomics Founder Isaiah Taylor

How Nuclear Will Unlock Energy Abundance with Valar Atomics Founder Isaiah Taylor

Valar Atomics founder Isaiah Taylor discusses how his company is rapidly advancing nuclear energy through hardware iteration, manufacturing, and a unique regulatory pathway. He explains their intrinsic safety philosophy, the strategic importance of vertical integration for speed and cost reduction, and their venture-backed approach to building gigasites. Taylor highlights how the demand for AI compute is a major driver for nuclear, showcasing their direct powering of an NVIDIA Blackwell chip, and casts a compelling vision for a future of "hyper-technoindustrialism" enabled by abundant, cheap atomic energy.

Technology

View All
Are Your Tests Slowing You Down? • Trisha Gee • GOTO 2025

Are Your Tests Slowing You Down? • Trisha Gee • GOTO 2025

Trisha Gee delivers a compelling talk on Developer Productivity Engineering (DPE) for testing, dissecting common pain points in writing, troubleshooting, and running tests. She advocates for strategic use of IDEs, advanced tooling like build caches and predictive test selection (leveraging ML), and a disciplined approach to test design to overcome these challenges, emphasizing that good tests serve as crucial living documentation.

The new post-quantum cryptography executive order. Plus: What is Q-Day, really?

The new post-quantum cryptography executive order. Plus: What is Q-Day, really?

This episode delves into Q-Day, the anticipated future when quantum computers can break public key cryptography, and the U.S. Executive Order accelerating the transition to post-quantum cryptography. Experts discuss why Q-Day is a gradual process rather than a sudden event, the critical importance of "crypto-agility" as a long-term strategy, and the necessity for organizations to begin immediate discovery and planning to secure data against "collect now, decrypt later" threats. The discussion also touches upon the broader, transformative benefits of quantum computing beyond just security.

Plenary Talk 3​: Challenges and research opportunities for global hyperscale services

Plenary Talk 3​: Challenges and research opportunities for global hyperscale services

Jim Kleewein's talk outlines the immense challenges and critical research opportunities in building and operating global hyperscale services like Microsoft 365 and Azure. He emphasizes that at this scale, traditional approaches fail, necessitating a "new golden age of applied research" across areas like continuous availability, data management, security, and sustainability. Kleewein also discusses AI's powerful but limited role, stressing the ongoing need for human expertise, and highlights the ethical imperative to prevent failures that can have life-or-death consequences.

Recent Post

Spec-Driven Development: Sharpening your AI toolbox - Al Harris, Amazon Kiro

Spec-Driven Development: Sharpening your AI toolbox - Al Harris, Amazon Kiro

Spec-Driven Development offers a structured, reproducible, and reliable alternative to 'vibe coding' in the AI era. Al Harris from the Kiro team explains how to leverage specs as living documentation, integrate external tools via MCPs, and use property-based testing to create a tight feedback loop from natural language requirements to verified code.

CES 2026 AI highlights: NVIDIA Rubin & wild gadgets

CES 2026 AI highlights: NVIDIA Rubin & wild gadgets

This episode explores the strategic implications of the Disney-OpenAI licensing deal, critiques Time Magazine's "Architects of AI" focus on business over research, analyzes NVIDIA's full-stack ambitions with the Neotron 3 model release, and delves into Anthropic's unique approach to AI safety with the "Claude Soul Document".

Java Generics and Collections • Maurice Naftalin & Stuart Marks

Java Generics and Collections • Maurice Naftalin & Stuart Marks

Maurice Naftalin and Stuart Marks discuss the second edition of "Java Generics and Collections," 19 years after the first. They explore the evolution of Java from version 5 to 25, focusing on major shifts like the move toward immutability, the introduction of sequenced collections and streams, and the critical design principles of collection encapsulation. The conversation delves into the anemic domain model anti-pattern, the controversial `UnsupportedOperationException`, and the framework's inconsistent null handling, reflecting on decades of experience with the Java Collections Framework.

CES 2026 AI highlights: NVIDIA Rubin & wild gadgets

CES 2026 AI highlights: NVIDIA Rubin & wild gadgets

The panel discusses the implications of the Disney-OpenAI licensing deal, arguing it represents a strategic platform play by Disney to control fan-generated content. They also analyze Time Magazine's 'Architects of AI', the business strategy behind Nvidia's Neotron 3 launch, and the unique fine-tuning approach revealed in Anthropic's Claude 'soul document'.

KDD '25 AI Reasoning Day keynote: Improving AI Reasoning through Intent, Interaction, and Inspection

KDD '25 AI Reasoning Day keynote: Improving AI Reasoning through Intent, Interaction, and Inspection

A deep dive into practical strategies for improving AI reasoning in code and structured tasks. The talk covers capturing richer user intent through examples, enabling collaborative interaction, and using automated inspection for iterative refinement, illustrated with real-world applications from Microsoft.

DSPy: The End of Prompt Engineering - Kevin Madura, AlixPartners

DSPy: The End of Prompt Engineering - Kevin Madura, AlixPartners

An in-depth guide to DSPy, a framework for programming with language models, not just prompting them. Learn its core concepts—Signatures, Modules, Adapters, and Optimizers—and see real-world examples of building robust, testable, and transferable AI applications for the enterprise.

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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