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 video tackles the overwhelming choice of agentic AI frameworks by categorizing projects into five types: linear workflows, autonomous multi-agent systems, role-based AI, production orchestration, and rapid prototyping. It details each type with examples and recommends specific frameworks like LangChain, AutoGen, and CrewAI, guiding developers to select the optimal tool based on their system design and real-world needs.
Booking Holdings CEO Glenn Fogel discusses his journey from Priceline's early struggles to leading a global travel giant. He details Booking's strategic adoption of AI for agentic travel planning and customer service, exemplified by Priceline's 'Penny,' and its significant capital investment in technology. Fogel emphasizes continuous innovation over "moats" and shares insights on AI's impact on job displacement, advocating for proactive employee upskilling to navigate the rapidly changing technological landscape.
Modal CTO Akshat Bubna discusses the company's shift from developer to agent experience, highlighting why traditional cloud infrastructure fails for bursty AI workloads. He details Modal's primitives like elastic inference with GPU snapshotting and speculative decoding, agent sandboxes for RL rollouts, multi-node training with RDMA, and a "supercloud" strategy across 17 providers. The conversation also covers the importance of observability, hard guardrails for production agents, and AI's role in making infrastructure exciting again.
Sara Bergman presents a practical guide on migrating .NET services to ARM-based architectures to achieve significant energy efficiency, cost savings, and performance per watt. She details the advantages of RISC over CISC, offers real-world examples, and provides a step-by-step .NET migration journey, emphasizing the importance of staying current with .NET, leveraging compilers, and strategically integrating ARM into development and deployment pipelines.
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.
Eric Peter from Databricks outlines the evolution from the traditional MLOps lifecycle to the more complex Agent Ops lifecycle. He details the five essential components of a successful agent development platform and introduces MLflow 3.0, a new release designed to provide a comprehensive, open-standard solution for building, evaluating, and deploying AI agents.
The Western mining industry is broken, hampered by a talent drain, slow technology adoption, and misaligned incentives. A new, vertically integrated, software-first approach leveraging Reinforcement Learning (RL) and LLMs can build and operate mines and refineries faster, cheaper, and more flexibly, addressing critical geopolitical supply chain risks.
Sherwood Callaway of 11X discusses the architecture of "Alice," an AI Sales Development Representative. He covers the practical decision to use LangGraph for its reliability in production, the challenges of infrastructure and observability when using hosted agent platforms, and their methodology for running Evals to mitigate hallucinations by comparing generated content against source data.
Developing general-purpose robots requires a shift from specialized, single-task systems to broad foundation models. This is achieved through a combination of large-scale, diverse, real-world data collection and a specific training methodology: pre-training on all available data and then fine-tuning on a curated, high-quality subset of demonstrations. This recipe, combined with architectural innovations to preserve the capabilities of Vision-Language Model (VLM) backbones, enables robots to perform complex, long-horizon tasks, generalize to unseen environments, and respond to open-ended human instructions.
Zohar Bronfman discusses why current LLMs are not on a path to AGI, contrasting their combinatorial creativity with the transformational, domain-general intelligence of humans. He argues that predictive models, not generative ones, deliver the most business value and explains how his platform, Pecan AI, automates the critical data preparation bottleneck to democratize predictive analytics for all businesses.
The OpenAI team details the creation of a new, powerful AI agent in ChatGPT, achieved by unifying the Deep Research and Operator models. They cover its unified architecture with shared state across tools, the reinforcement learning techniques used for training, and the critical safety measures required for an agent that can take real-world actions.
Get updates straight to your inbox. No spam, just useful content.