Interactive discovery
Follow the connections between themes, people, and ideas across the Tokenless archive in an interactive topic modeling map.
SWE-Marathon introduces a benchmark for long-horizon autonomous software engineering, pushing coding agents from bug fixes to full project ownership. It highlights the critical need for robust, multi-layered verification and anti-cheat mechanisms to prevent reward hacking in tasks spanning hundreds of millions of tokens, revealing that current agents achieve only a 26% success rate.
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.
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.
The UK Ministry of Justice Justice AI Unit operates as a startup within government, deploying engineers directly into prisons and probation offices. This 'forward deployed' model enables rapid, user-centric AI product development, overcoming bureaucratic hurdles by prioritizing real-world feedback and agile implementation to empower frontline staff and solve critical operational challenges.
Victoria Melnikova discusses optimal Go-To-Market strategies for developer tools and AI startups, asserting that a founder's personal brand is the most underrated competitive advantage in 2026. She covers foundational GTM hygiene, the strategic importance of San Francisco, effective advertising and event tactics, embracing unconventional marketing, and the critical role of authenticity and personal connection in building trust and cutting through digital noise.
Rajiv Chandegra introduces adaptive engineering, a new AI design philosophy. He argues that as AI models become more powerful and interact with complex, dynamic real-world problems, the traditional 'fixed harness' approach—predictable but brittle—will become obsolete. Drawing on complexity science, he explains how adaptive engineering allows the AI system's structure (harness) to emerge and adapt dynamically during runtime, mirroring natural self-organizing systems. This shift redefines the engineer's role to designing constraints and fostering horizontal intelligence in multi-agent coordination.
Zipline co-founder Keller Rinaudo Cliffton and Eric Watson discuss how their autonomous logistics system evolved from addressing critical needs in Rwanda to becoming the largest commercial autonomous system globally. They highlight that the drone is only 15% of the solution, emphasizing the deep integration of software, vertical hardware design, advanced safety protocols like compute failover, and extensive testing required. The discussion also covers the immense market potential for autonomous delivery, the impending cost-effectiveness over traditional methods, and the necessary transformation of air traffic control to support a future of pervasive aerial autonomy.
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.
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.
Amanda Downie explains the shift from reactive IT firefighting to proactive optimization, detailing how AI agents and LLMs use predictive analytics, topology mapping, and continuous learning loops to anticipate and prevent system issues before they occur.
Jan Oberhauser, founder of n8n, discusses the company's strategic pivot from a workflow tool to an AI automation platform. He explains how focusing on community, adopting a "connect everything to anything" philosophy, and enabling the creation of complex AI agents led to a 4x revenue increase in just eight months.
A discussion on refining patient questions for a study on diabetes, highlighting the contrast between simplified questions for scalable data collection and the complex, nuanced queries from long-term patients. The team explores how to test their AI-driven storytelling system with these specific, real-world scenarios to generate more grounded and relevant health narratives.
Dexter Horthy of Human Layer explains why naive AI coding agents fail in complex software projects and introduces 'Advanced Context Engineering.' He details a spec-first, three-phase workflow (Research, Plan, Implement) designed to manage context intentionally, keeping utilization below 40% to maximize model performance. This approach uses subagents and frequent compaction to turn AI from a prototyping tool into a production-ready system for large, brownfield codebases.
Sam Bhagwat of Mastra details their process for optimizing AI agent memory using the Long Mem Eval benchmark. He breaks down memory into subtasks like temporal reasoning and knowledge updates, and shares how targeted improvements—such as tailored templates, targeted data updates, and structured message formatting—led to state-of-the-art performance, emphasizing the importance of iterative evaluation.
Jeff Huber of Chroma argues that building reliable AI systems hinges on 'Context Engineering'—the deliberate curation of information within the context window. He challenges the efficacy of long-context models, presenting a 'Gather and Glean' framework to maximize recall and precision, and discusses specific challenges and techniques for AI agents, such as intelligent compaction.
Get updates straight to your inbox. No spam, just useful content.