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.
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.
An in-depth look into GPT Live, the next generation of full-duplex voice models in ChatGPT, designed for natural, continuous interaction. It highlights breakthroughs in concurrent processing, intelligent delegation to advanced models like GPT 5.5, real-time semantic translation, and proactive language coaching, aiming to transform AI interactions into fluid, intelligent conversations akin to human dialogue.
Theo Browne's keynote from AIEWF2026 urges software engineers to fundamentally change product development in response to rapidly evolving AI models (Sonnet 3.5 to Mythos). He advocates for rejecting legacy mental models and tools (skeuomorphism), embracing a new "Markdown tier" for projects, and thinking "wider" instead of just "deeper" by building extensible platforms that can challenge industry giants. The core message is to be more ambitious, as AI has drastically lowered the barrier to entry for complex, broad-reaching solutions.
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.
A breakdown of key findings from the IBM 2025 Cost of a Data Breach Report, focusing on the financial impact of breaches, the dual role of AI in attacks and defense, primary threat vectors, and actionable recommendations for improving security posture.
Members of the OpenAI team, Alex Wei, Sheryl Hsu, and Noam Brown, discuss their model's historic gold-medal performance at the International Mathematical Olympiad (IMO). They detail their unique approach using general-purpose reinforcement learning for hard-to-verify tasks, the model's surprising self-awareness, and the vast gap that remains between solving competition problems and achieving true mathematical research breakthroughs.
Paul van der Boor and Sean Kenny from Prosus detail the journey of Toqan, an internal AI platform that evolved from a Slack experiment into a sophisticated agentic system. They share insights on driving enterprise adoption, key metrics for measuring productivity, and their future vision of an "AI Workforce" where employees architect AI agents to automate complex, cross-system tasks.
A summary of the talk by Harvey and LanceDB on building a highly optimized retrieval architecture for the legal profession. It covers challenges like query complexity and data scale, the importance of evaluation, and how LanceDB's multimodal lakehouse architecture provides the necessary foundation.
David Karam, formerly of Google Search, presents a pragmatic framework for enhancing RAG systems, advocating a "quality engineering" approach. The talk progresses through a ladder of techniques, from in-memory retrieval and BM25 to custom embeddings, re-ranking, and advanced orchestration, emphasizing that the choice of technique should be driven by empirical analysis of system failures ("loss analysis") and balanced by a "complexity-adjusted impact" mindset.
Jared Kaplan, co-founder of Anthropic, explains how the discovery of predictable, physics-like scaling laws in AI training provides a clear roadmap for progress. He details the two main phases of model training (pre-training and RL), discusses how scaling compute predictably unlocks longer-horizon task capabilities, and outlines the remaining challenges—memory, nuanced oversight, and organizational knowledge—on the path to human-level AI.
Get updates straight to your inbox. No spam, just useful content.