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.
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.
Mixedbread AI addresses the "Oracle Gap" – the disparity between LLM reasoning and retrieval capabilities – by developing agents trained to use advanced search tools effectively. They demonstrate how current LLMs generate poor queries due to training biases and introduce a sophisticated agent harness with diverse search tools and a unique training regimen, including supervised fine-tuning and reinforcement learning with custom rewards, to teach agents to form precise semantic queries. This approach significantly improves performance on benchmarks like Oblique Congress and Snowflake's Match QA, closing the gap between theoretical perfect retrieval and real-world agent performance.
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.
Jacob Helberg, Under Secretary of State designate, discusses how AI will act as a productivity engine to reindustrialize America, the geopolitical race for AI dominance in the "superintelligence century," and the critical need for nuclear energy to power this transformation.
Sequoia Capital's Konstantine Buhler presents an investment thesis on the AI-driven "Cognitive Revolution," framing it as a transformation larger and faster than the Industrial Revolution. The core of the thesis is the $10 trillion opportunity in automating the US services market and the shift in work from certainty to high leverage. Buhler outlines five current investment trends, including real-world validation over academic benchmarks and compute as the new production function, and five future themes Sequoia is betting on, such as persistent memory, AI-to-AI communication, and AI security.
Nikolaos Vasiloglou, VP of Research ML at RelationalAI, shares his extensive analysis of the 2023 NeurIPS conference, distilling over 200 hours of content. Key themes include the dominance and evolution of agentic AI, the state of open-source vs. frontier LLMs, the first signs of deep learning models outperforming XGBoost on tabular data, and the critical rise of verification systems. He also explores the future of AI with data attribution for monetization and the concept of composable, LEGO-like language models.
In the fifth edition of the a16z Consumer AI 100, an analysis of the most-used AI-native products reveals a market that is beginning to stabilize after a period of chaotic growth. Key trends identified include the continued dominance of AI companionship and creative tools, the significant market entry of major players like Google and xAI's Grok, the rise of Chinese AI companies on the global stage, and the emergence of a powerful new category: "vibe coding." The data suggests a future of increased verticalization, prosumer tool adoption, and the development of more sophisticated network effects beyond simple data acquisition.
Daniel Terhorst-North explores the learnable traits of great programmers, challenging the notion of innate talent. He outlines a three-part framework focusing on effective execution, selecting appropriate tools, and fostering a psychologically safe team environment, emphasizing that greatness is achieved through deliberate practice and a focus on product and people over code.
Lak Lakshmanan presents a robust architecture for building production-quality, framework-agnostic agentic systems. He advocates for using simple, composable GenAI patterns, off-the-shelf tools for governance, and a strong emphasis on a human-in-the-loop design to create continuously learning systems that avoid vendor lock-in.
Get updates straight to your inbox. No spam, just useful content.