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 detailed summary of a talk by Jeff Huber (Chroma) and Jason Liu on systematically improving AI applications. The talk covers using fast, inexpensive evaluations for retrieval systems (inputs) and applying structured data analysis and clustering to conversational logs (outputs) to derive actionable product insights.
Omar Khattab, creator of DSPy, reinterprets the 'Bitter Lesson' for AI engineering, arguing that the key to building robust and enduring AI systems is to move beyond brittle prompt engineering. He advocates for a declarative, modular approach that separates the fundamental program logic from the rapidly changing landscape of LLMs, optimizers, and inference techniques.
Ido Pesok from Vercel explains why LLM-based applications often fail in production despite successful demos, and presents a systematic framework for building reliable AI systems using application-layer evaluations ("evals").
A deep dive into why 2025 is poised to be the 'Year of Evals' for AI. The speaker argues that a confluence of factors—the C-suite's post-ChatGPT awakening, budget dynamics, and the rise of autonomous agentic systems—has finally made AI evaluation a critical, top-of-mind issue for enterprise leaders.
Itamar Friedman of Qodo argues that the future of AI in software development lies in moving beyond simple code generation to 'vibe coding with confidence.' This is achieved through multi-agent workflows, grounded in team standards and orchestrated via the Command Line Interface (CLI), enabling a holistic AI-driven approach across the entire SDLC.
Tanmai Gopal, CEO of Hasura, discusses a Gen AI-driven automation strategy that addresses the "Automation Paradox" by empowering non-technical users. This approach uses a domain-specific language (DSL) to translate natural language into deterministic, executable plans, aiming to drive over $100M in annual impact for a healthcare partner.
Get updates straight to your inbox. No spam, just useful content.