Aswin Majjiga·19h agoThoughts on AI trendsThese are my notes on how we got here, what could drive the future of AI and what it means to run a technical team in the AI era
Bruno Boucard·3d agoAgent Harnesses (1/3): Why Yesterday’s Best Practices Are Costly TodayTable of Contents
Christiaan Huizer·4d agoFrom Rows to Reasoning with CodaHow blending tables and canvas led to modern AI pipelines
Pablo Demian Rebolini·Nov 4Beyond a Successful Bypass: What 30 Controlled Trials Reveal About Agent Security BoundariesEngineering Trust in Autonomous Agents · Agent Under Control · PUB-003
Ashrith Jacob·Nov 2The Era of “always on” agentsGrok Bot, launched in beta on August 11 — always-on agents with their own cloud computer that sign into your tools, finish jobs end to end…A response icon1A response icon1
InTowards AIbyHubert Nakielski·Oct 30I Ran One Fake Hostile Agent Through Five Sandboxes on My MacSeatbelt, a hardened container, Docker Sandboxes, gVisor and Firecracker against the same canary: how to set each one up, what it stopped…
Ashutosh Jha·Oct 26I Read the AI Agent Code. The Model Wasn’t the Interesting Part.how I stopped blaming the LLM and started reading the 400 lines of Python wrapped around it.
Pablo Demian Rebolini·Oct 25The Agent Is Not the Security BoundaryWhat two incident-recovery experiments reveal about prompt injection, tool authorization, and the engineering of reliable autonomous…
Breath of Code·Oct 25The 8 Components of an AI Harness — Beyond Prompt EngineeringA component-by-component tour of the eight editable pieces of Google Harness²
