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.
Drawing from conversations with top AI builders, Dex argues that production-grade AI agents are not magical loops but well-architected software. This talk introduces "12-Factor Agents," a methodology centered on "Context Engineering" to build reliable, high-performance LLM-powered applications by applying rigorous software engineering principles.
This talk introduces Eval-Driven Development (EDD) as a scientific alternative to 'vibe-based' iteration for improving AI agents. It covers quantitative evaluation (choosing strong end-to-end metrics, aligning LLM judges) and qualitative evaluation (using error and attribution analysis to debug failures), providing a structured framework for consistent agent improvement.
Robert from Emergent Methods discusses how grounded synthetic news data can solve the publisher revenue crisis in the AI era. He details the process of 'Context Engineering' news into token-optimized, objective data for high-stakes AI agent tasks, covering their open-source models for entity extraction and bias mitigation, and the on-premise infrastructure that protects publisher content.
Ryan Fox-Tyler from Hypermode explains their philosophy of empowering AI agents to design and deploy other agents. He introduces Concierge, an agent that builds other agents, and details the underlying actor-based runtime built for scalability, fault tolerance, and efficient, event-driven execution of thousands of parallel agent instances.
Simba Khadder explains that the primary bottleneck for LLM agents is not intelligence, but access to structured data. He introduces EnrichMCP, an open-source framework that creates a semantic layer over data models, enabling agents to discover, reason about, and query data sources like SQL databases effectively, moving beyond the limitations of RAG and direct API conversions.
Marit van Dijk and Hannes Lowette discuss why reading code is a critical, yet underdeveloped, skill for software developers. They explore research-backed strategies like structured code reading clubs, leveraging modern IDEs and AI assistants to comprehend complex codebases, and the importance of empathy in code reviews. The conversation emphasizes using tests as documentation and writing clear commit messages to improve collaboration and long-term maintainability.
Get updates straight to your inbox. No spam, just useful content.