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.
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.
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.
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.
Devin Stein, CEO of Dosu, discusses a new paradigm for knowledge management where an AI agent learns from code, conversations, and tickets to create an 'eventually consistent' knowledge base. The conversation explores the lifecycle of facts, the challenges of agent interaction, and the future of documentation in a world of collaborating AI agents.
Brian Balfour, founder of Reforge, explains the predictable four-step cycle of technology platforms, from open to closed, and argues that ChatGPT is about to enter the "open" phase, creating a massive, time-sensitive distribution opportunity that startups and incumbents alike cannot afford to ignore.
Google DeepMind researchers Jack Parker-Holder and Shlomi Fruchter detail the creation of Genie 3, a model that generates interactive, persistent worlds from text in real time. They cover its breakthrough spatial memory, emergent physical intuition, and its potential to revolutionize gaming, robotics, and AI agent training.
Bob Kalka from IBM and Tyler Lynch from HashiCorp discuss the critical disconnect between managing human and non-human identities, which contributes to 80% of all cyberattacks. They introduce the concept of an 'Identity Fabric'—an AI-augmented approach to unify existing tools—and outline six key use cases and a three-phase strategy to address modern identity and access management (IAM) challenges.
Ben Lorica and Evangelos Simoudis analyze three pivotal AI trends: the "Great Hollowing Out" of entry-level jobs, the financial disconnect between AI hardware depreciation and its useful life, and OpenAI's strategic shift to router-based models in the quest for a sustainable business model.
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.
Get updates straight to your inbox. No spam, just useful content.