Tokenless

Tokenless

Session on Reasoning

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
Session on Reasoning

Session on Reasoning

This session features two talks on optimizing and verifying AI reasoning. Hongxiang Fan discusses cross-stack co-design for efficient AI, focusing on Test-Time Scaling (TTS) challenges, optimal verification granularity, and system-level optimizations for edge deployments. Nagarajan Natarajan introduces 'Advancing Verified Reasoning' with the InterVent platform, aiming to ensure AI agents comply with complex policies through formal verification, dynamic steering, and leveraging verification signals for training. Both emphasize addressing the computational and reliability costs of advanced AI.

Multimodal & Embodied Intelligence (Pt 1), Panel on Multimodal AI: Progress, Pitfalls, Possibilities

Multimodal & Embodied Intelligence (Pt 1), Panel on Multimodal AI: Progress, Pitfalls, Possibilities

This session explored Multimodal and Embodied Intelligence, featuring talks on hybrid AI in robotics (classical vs. end-to-end), AI's role in healthcare (focusing on NCDs, deployment, and uncertainty modeling), and fundamental perception challenges in multimodal reasoning (using educational video QA and visual puzzles). A panel discussed the impact of foundation models, the blurred lines between AGI and human-like AI, critical deployment pitfalls (human factors, efficiency, architectural limits), and future directions, emphasizing task-specific models and the redefinition of 'foundation models.'

Grant Sanderson (@3blue1brown) – AI and the future of math

Grant Sanderson (@3blue1brown) – AI and the future of math

Grant Sanderson and Dwarkesh Patel discuss AI's rapid but uneven progress in mathematics, exploring whether AI can achieve true conceptual breakthroughs, the challenge of measuring creativity, and the long-term implications for human understanding and the future roles of mathematicians. They delve into the unique 'grindability' of math for AI training, the potential of formalization, and why AI currently struggles with 'theory of mind' in writing, offering advice for students navigating an AI-transformed world.

Technology

View All
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.

Platforms: Build Abstractions, not Illusions • Gregor Hohpe • GOTO 2025

Platforms: Build Abstractions, not Illusions • Gregor Hohpe • GOTO 2025

Gregor Hohpe explains the critical role of platforms in managing the growing cognitive load on developers due to complex distributed systems. He contrasts platforms, driven by "economies of speed" and fostering innovation through diversity, with traditional IT services and oversimplified abstractions that create dangerous illusions. Hohpe emphasizes building platforms that provide intuitive, domain-specific abstractions to solve real business problems, rather than just repackaging existing cloud services.

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.

Recent Post

Beyond the Hype: What AI Actually Can (and Can't) Do • Jodie Burchell & Michelle Frost • GOTO 2026

Beyond the Hype: What AI Actually Can (and Can't) Do • Jodie Burchell & Michelle Frost • GOTO 2026

Jodie Burchell and Michelle Frost of JetBrains offer a measured, research-grounded perspective on the state of generative AI. They discuss the shifting definitions of AI, the enduring importance of foundational machine learning principles, historical parallels to previous 'AI summers,' the measurement problem of AGI, and what the evidence actually says about AI's impact on developer productivity.

Agentic Runtime Security Explained: Securing Non‑Human Identities

Agentic Runtime Security Explained: Securing Non‑Human Identities

Agentic AI introduces a massive number of non-human identities that traditional, human-centric Identity and Access Management (IAM) systems are not equipped to handle. This creates significant security gaps, including lack of accountability, overprivilege, risky delegation, and the dangerous 'last mile' problem. The solution lies in adopting a Zero Trust approach with five key imperatives: registering all agents, stripping static privileges for just-in-time access, tying actions to intent, enforcing security at the point of use, and proving control through comprehensive audits. Implementing this requires a combination of orchestration, governance, and unified observability across security, IT, and development teams.

⚡️Monty: the ultrafast Python interpreter by Agents for Agents — Samuel Colvin, Pydantic

⚡️Monty: the ultrafast Python interpreter by Agents for Agents — Samuel Colvin, Pydantic

Sam Khavari, the creator of Pydantic, introduces Monty, a new, secure, and high-performance Python interpreter written in Rust. Monty is designed specifically for AI agents, bridging the gap between simple, limited tool-calling and complex, slow, full-featured sandboxes.

Solving the Wrong Problem Works Better - Robert Lange

Solving the Wrong Problem Works Better - Robert Lange

Robert Lange from Sakana AI discusses Shinka Evolve, a framework combining LLMs with evolutionary algorithms for open-ended program search. The conversation explores how Shinka Evolve addresses the limitations of systems like AlphaEvolve by co-evolving problems and solutions, its sample-efficient architecture using UCB bandits and quality-diversity search, and its applications in circle packing, competitive programming, and evolving MoE loss functions. The discussion also delves into the philosophical debate on whether these systems produce true novelty or are parasitic on their starting conditions, and the future role of the "AI Scientist" as a human co-pilot.

Under Secretary of War on Iran, Anthropic and the AI Battle Inside the Pentagon | The a16z Show

Under Secretary of War on Iran, Anthropic and the AI Battle Inside the Pentagon | The a16z Show

Emil Michael, a key figure in the Department of Defense, outlines his strategy for modernizing the department by prioritizing Applied AI. He details the risks discovered in existing commercial AI contracts, which led to a vendor-lock crisis, and explains how the DoD is reforming its procurement processes to better engage with innovative startups and ensure technology serves national security interests without restrictive terms.

Architecture for Flow • Susanne Kaiser & James Lewis

Architecture for Flow • Susanne Kaiser & James Lewis

In an interview with James Lewis, Susanne Kaiser discusses her book "Architecture for Flow," which synthesizes Domain-Driven Design, Wardley Mapping, and Team Topologies. She explains how this holistic approach helps design adaptive socio-technical systems by starting with the problem space, visualizing the value chain, and aligning team structures to the software architecture, all guided by her practical "Architecture for Flow Canvas."

← PreviousNext →

Stay In The Loop! Subscribe to Our Newsletter.

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