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.
A deep dive into using Google's A2A (Agent-to-Agent) framework and MCP (Model Context Protocol) to build intelligent, automated workflows. This summary covers the core concepts, strategic implementation, a practical multi-agent architecture, and critical insights on lean context management to control costs and latency.
GitHub's Christopher Harrison explains how to leverage GitHub Copilot's agent capabilities. This summary covers using Copilot as an AI pair programmer, the importance of providing context, its different workloads, and how to use the new Copilot Coding Agent with the Model Context Protocol (MCP) to accelerate development responsibly.
Explore the shift from traditional, human-driven software development to an agent-native lifecycle. Learn how AI agents, powered by centralized context, can orchestrate the entire SDLC, from planning and coding to incident response, transforming developers into orchestrators of AI systems.
Josh Albrecht, CTO of Imbue, discusses the engineering challenges in building reliable AI coding agents. He introduces Sculptor, an experimental environment designed to build trust in AI-generated code by focusing on preventing and detecting problems through structured workflows, automated testing, and AI-driven analysis, moving beyond simple code generation to create maintainable software.
Explore the shift from manual coding to AI-driven development. This session covers the mechanics of AI coding agents like OpenHands, best practices for using them effectively without accumulating tech debt, and practical use cases, emphasizing the continued importance of human oversight and critical thinking in software engineering.
Scott Wu, CEO of Cognition AI, discusses the exponential growth of AI capabilities in software engineering, likening it to a "Moore's Law for AI agents" with a doubling time of every 70 days. He chronicles the evolution of their AI agent, Devin, from handling repetitive code migrations to autonomously managing entire backlogs, highlighting the key technical challenges and paradigm shifts at each stage.
Get updates straight to your inbox. No spam, just useful content.