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.
OpenAI's Romain Huet and Alexander Embiricos, joined by Peter Steinberger, outline the explosive progress of Codex at Dev Day 2024. They highlight the shift from manual coding to managing autonomous agents, enabled by rapid model iteration (every 6 weeks), open-source developer tools, and optimizations for cost-effectiveness ($1/M input tokens) and blazing inference speed (750 tokens/sec). The discussion centers on empowering AI engineers, not replacing them, by evolving agent capabilities, fostering an open ecosystem, and addressing future challenges like seamless local/cloud task execution and human attention as the new bottleneck in agent orchestration.
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.
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.
Misha Laskin, co-founder of Reflection AI and former researcher at Google DeepMind, discusses the company's mission to build superhuman autonomous systems. He introduces Asimov, a code comprehension agent designed to solve the 80% of an engineer's time spent on understanding complex systems, rather than just code generation. Laskin delves into the intricacies of co-designing product and research, the critical role of customer-driven evaluations, the bottlenecks in scaling reinforcement learning (RL) — particularly the "reward problem" — and why he believes the future is one of "jagged superintelligence" emerging in specific, high-value domains like coding.
John Jumper, one of the creators of AlphaFold, discusses the journey of developing an AI system to solve the protein folding problem. He emphasizes that the breakthrough was driven more by novel research and a combination of "mid-scale ideas" than by raw data or compute scale alone. The talk covers the importance of blind-assessment benchmarks like CASP, the strategy of releasing a massive, accessible database to drive adoption and trust, and the unexpected ways the scientific community used the tool. He concludes by framing AI for science as a powerful amplifier for experimentalists, accelerating discovery by generating high-quality, testable hypotheses.
Pushmeet Kohli, head of AI for Science at DeepMind, discusses AlphaEvolve, an AI system that uses Large Language Models (LLMs) coupled with evolutionary search to discover novel, human-interpretable algorithms. He explains the architecture, from its predecessor FunSearch to the multi-agent "Co-scientist" system, and details breakthroughs in solving decades-old math problems and optimizing real-world systems like data center scheduling and chip design.
André Prager, former Chief Engineer at Wing, discusses the core engineering philosophy of simplicity and cost-effectiveness that enabled the drone delivery service. He covers the design of key systems like the passive charging pad, the intelligent winch, the non-powered autoloader, and the iterative process of making the drones acoustically unobtrusive.
Yishay Carmiel and Roy Zanbel of Apollo Defend explore the state of voice AI, detailing the shift from cascaded models to end-to-end speech-to-speech systems. They break down the imminent security threats, including accessible voice cloning and sophisticated agent-based attacks, and discuss the nascent defense mechanisms and the urgent need for a new layer of voice security for governments, enterprises, and consumers.
Jonathan Blow, creator of Braid and The Witness, discusses the design philosophy behind 'jai', a new systems programming language. He explains how 'jai' re-evaluates the cost-benefit analysis of manual memory management by providing powerful, low-friction tools for metaprogramming, introspection, and debugging, inspired by principles from functional programming.
Get updates straight to your inbox. No spam, just useful content.