Posts

Upwork's Radical Bet on Reinforcement Learning: Building RLEF from Scratch | Andrew Rabinovich (CTO)

Upwork's Radical Bet on Reinforcement Learning: Building RLEF from Scratch | Andrew Rabinovich (CTO)

Andrew Rabinovich, CTO and Head of AI at Upwork, details their strategy for building AI agents for digital work. He introduces a custom reinforcement learning approach called RLEF (Reinforcement Learning from Experience), explains why digital work marketplaces are ideal training grounds, and shares his vision for a future where AI delivers finished projects, orchestrated by a meta-agent named Uma.

No Priors Ep. 132 | With Decagon CEO and Co-Founder Jesse Zhang

No Priors Ep. 132 | With Decagon CEO and Co-Founder Jesse Zhang

Jesse Zhang, co-founder and CEO of Decagon, discusses how their AI agents are revolutionizing customer service for large enterprises by replacing mundane human labor. He covers their go-to-market strategy, the importance of a hardworking in-office culture, his journey as a second-time founder, and the future of an agentic world where AIs interact on behalf of companies and consumers.

Production monitoring for AI applications using W&B Weave

Production monitoring for AI applications using W&B Weave

Learn how W&B Weave's online evaluations enable real-time monitoring of AI applications in production, allowing teams to track performance, catch failures, and iterate on quality over time using LLM-as-a-judge scores.

Beyond Prompting: The Emerging Discipline of Context Engineering Reading Group

Beyond Prompting: The Emerging Discipline of Context Engineering Reading Group

This summary covers a deep dive into the paper "A Survey of Context Engineering for Large Language Models". The discussion reframes the conversation from simple prompt engineering to a more systematic approach of building information environments for LLMs. It explores the foundational components of context engineering—generation, processing, and management—and their application in advanced systems like Retrieval-Augmented Generation (RAG), memory, tool use, and multi-agent systems.

Hands-on Demo of Glamorous Toolkit & Moldable Development • Tudor Girba & Kris Jenkins • GOTO 2024

Hands-on Demo of Glamorous Toolkit & Moldable Development • Tudor Girba & Kris Jenkins • GOTO 2024

Tudor Girba introduces "Moldable Development," a paradigm where developers create thousands of custom tools to analyze and interact with their specific software context. He demonstrates this live using Glamorous Toolkit, transforming an unstructured text file into a browsable system with custom views, all within minutes.

AI ransomware, hiring fraud and the end of Scattered Lapsus$ Hunters

AI ransomware, hiring fraud and the end of Scattered Lapsus$ Hunters

Experts from IBM X-Force discuss the alleged retirement of the Scattered Lapsus$ Hunters cybercrime gang, the ethics and implications of AI-powered ransomware, critical software supply chain vulnerabilities exposed by the recent npm hack, growing threats to Operational Technology (OT), and the emergence of AI-driven hiring fraud.