» Tag
ai
1052 postsYour AI agent says "done." Who checks that from outside the agent?
The issue of AI agents reporting false completions is critical for engineers, highlighting the need for independent verification.
I Built a Firewall for My AI Agents: The Near-Miss That Prompted It
Bastion Gateway enhances AI agent security. Learn about the near-miss experience and the security measures implemented.
How to Escalate an AI Email Agent's Thread to a Human
Steps and methods for escalating AI email agent threads to human reviewers.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comTurboQuant: Four Months After Google's 6x VRAM Claim
Google's TurboQuant algorithm aimed for a 6x memory reduction, but official code is still not released.
Your RAG Eval Is Checking the Receipt, Not the Patient
Explore the risks of entity attribution failures in clinical RAG systems and how to improve evaluations.
SociaLLM Engineering: Manipulating AI Agents and Solutions
SociaLLM engineering explores methods to manipulate AI agents. A crucial topic for engineers.
The Wrong Number: Origin Part 19
In Origin Part 19, misconfigurations and overlaps in training data were uncovered.
An AI Agent at the Border: Implications for the Future
Insights on AI agents' document verification and the impact of regulations.
No Confirmed Details on Claude Opus 5 Release
The release date for Claude Opus 5 is uncertain. Anthropic emphasizes the need for a new model.
Learning AI Orchestration and Harness Engineering for Autonomous Systems
Insights on AI orchestration and harness engineering through an autonomous engineering project.