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.
Aytekin Tank, Founder and CEO of Jotform, discusses how AI is revolutionizing software development and customer support, highlighting "vibe coding" and Jotform's 80% AI-handled support with zero layoffs. He also shares his "Theory of Constraints" playbook for scaling businesses and explores the potential of ChatGPT apps, all within Jotform's 20-year bootstrapped journey.
This session explores building an AI coding agent that integrates with the Agent Client Protocol (ACP), Zed's open-source JSON RPC-based standard for agent-client communication. It covers essential architectural elements, including protocol design, session lifecycle management, real-time streaming of model output via session updates, and sophisticated handling of tool calls, such as proxied file system operations and self-modifying code for new capabilities like a terminal tool.
This podcast explores the critical role of safeguards in frontier AI models like Anthropic's Fable 5 and OpenAI's GPT-5.6 Sol, analyzing the tension between powerful capabilities and misuse prevention. It also dissects the emergence and debate around agentic ransomware, specifically Jade Puffer, and covers the rise of ClickFix as a dominant social engineering attack targeting developers. Finally, it provides an in-depth analysis of UnregStealer, a credential-theft campaign impacting Latin American financial institutions, detailing its attack chain and mitigation strategies.
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.
Members of Anthropic's interpretability team discuss their research into the inner workings of large language models. They explore the analogy of studying AI as a biological system, the surprising discovery of internal "features" or concepts, and why this research is critical for understanding model behavior like hallucinations, sycophancy, and long-term planning, ultimately aiming to ensure AI safety.
OpenAI's Chief Scientist Jakub Pachocki and researcher Szymon Sidor discuss the rapid progress towards AGI, focusing on the shift from traditional benchmarks to real-world capabilities like automating scientific discovery. They share insights into recent breakthroughs in mathematical and programmatic reasoning, highlighted by successes in competitions like the International Math Olympiad (IMO), and explore what's next for scaling and long-horizon problem-solving.
Casey Handmer explains why the massive energy demand from AI will be met not by the grid or natural gas, but by vast, off-grid solar farms, and what this energy singularity means for the future of civilization.
a16z's Martin Casado and Anjney Midha detail the dramatic shift in U.S. AI policy from a 'pause AI' stance, fueled by doomerism and flawed analogies, to a pro-innovation 'win the race' strategy. They discuss how China's progress shattered illusions of a U.S. lead, the strategic business case for open source AI, and the pragmatic promise of the new AI Action Plan.
Author Vlad Khononov discusses his book "Balancing Coupling in Software Design," explaining how a failed microservices project led him to rediscover timeless design principles from the 1970s. He explores the concepts of local vs. global complexity, the role of modularity as an antidote to complexity, and how managing coupling is crucial for building maintainable systems in any architectural style, from monoliths to cloud-native applications.
Experts from IBM discuss Perplexity's audacious bid for Google Chrome, analyzing it as a strategic marketing move and debating the browser's future as a key platform for enterprise AI. They also explore the future of generative video, questioning if it's a consumer or enterprise feature while highlighting critical IP and ethical hurdles. Finally, they assess the GPT-5 release, countering claims of an AI plateau and discussing user attachment to older models and the shift towards software-defined AI systems.
Get updates straight to your inbox. No spam, just useful content.