AI · Video
The Agents Were Fine, but Everything Around Them Broke, Says Harvey Engineer
AI Engineer ·
At a glance
Joey Wang, an engineer at Harvey, a legal AI company, describes what happened while running Spectre, the company's internal cloud agent platform. The experience involved handling 10,000 pull requests (proposed code changes) written by AI agents (programs that perform tasks on behalf of people).
Key points
- Engineers can choose the agent they want, but one platform takes responsibility for everything that happens after that.
- The system makes every action callable, so agents can control other agents. The article explains this structure.
- The article describes problems where alerts flooded in and created hundreds of tasks, clusters (systems that group multiple servers) filled up, and the merge queue backed up, along with the solutions.
Why it matters
If you are curious about where AI agents break first in real work, this article is worth reading.
Original source
The Agents Were Fine. Everything Around Them Broke. - Joey Wang, Harvey
AI Engineer · Nov 10, 11:00 KST
Watch on YouTube ↗AI summarized the video title and description. Check the original for accuracy. Copyright belongs to AI Engineer.
More from this field
- OpenAI Opens ChatGPT Space to Plus Users for Pages, Slides, and Team Sharing
OpenAI opened ChatGPT Space to Plus users on the 20th, local time. Space works as a new home for pages, slides, images, files, and uploads. Users can write pages with ChatGPT, add interactive charts, turn ideas into slides, and invite others to edit together.
AI 매터스 · Nov 21, 11:26 KST - Anthropic Researcher Claims Claude Helped Prove Riemann Hypothesis, Experts Await Review
Wes Roth covers a claim by Anthropic researcher Levent Alpöge that he proved the Riemann Hypothesis with help from the AI model Claude. He looks at the huge Lean formal proof, reactions from mathematicians and AI safety researchers, and what this could mean for AI and math.
Wes Roth · Nov 21, 11:24 KST - Amazon CloudWatch Omni Adds Microsoft Azure Logs, Metrics, and Traces Support
Amazon CloudWatch Omni can now collect Azure resource logs, Azure Monitor platform metrics, virtual network flow logs, and Application Insights traces. Teams running workloads on both AWS and Azure can view all of this telemetry in one place, without separate tools or custom pipelines.
AWS What's New · Nov 21, 10:10 KST - AWS Quick Adds Chat-Built Flows, Updated Web App, and Teamwork Among Agents
AWS Quick added updates that let a team turn one person's work routine into a shared, repeatable process. Flows can now be built and changed entirely in chat, and they can run from the web, desktop, or mobile app. Agents working together can also give more complete answers.
Amazon AWS Machine Learning blog · Nov 21, 10:06 KST