Reya Vir

PhD Student at Columbia University

[Towards Data Science @TDataScience]

How do you go about catching silent failures in your agentic coding pipelines? @ReyaVir presents a tool she built to help builders verify their app aligns with their intent. https://t.co/g4l8pPFsy1

[Reya Vir @ReyaVir]

Excited to be spending the summer at Google DeepMind as a PhD Student Researcher! Been here for a little over a month already, building AI agents for hardware/software co-design and learning a ton from an incredible team.

If you’re also around this summer, I’d love to chat!

[Towards Data Science @TDataScience]

If you're curious to understand why rigidly constrained agents fail, and how to engineer token-efficient, self-adapting workflows, don't miss the latest from @virrahul and @ReyaVir. https://t.co/emRoUQbzVJ

[Towards Data Science @TDataScience]

Learn how to engineer token-efficient, self-adapting agentic workflows by following along @virrahul and @ReyaVir's new and insightful article. https://t.co/emRoUQbzVJ

[Reya Vir @ReyaVir]

@sh_reya Congratulations Shreya!!

[DAPLab @DAP__Lab]

Calling all academic researchers working on AI Agents!! 👇

We’ve extended the deadline to April 6 for North East AI Agents Day — a one-day workshop in NYC bringing together _academic_ researchers across ML, Systems, and HCI pushing the frontier of agentic AI.

If you're building, studying, or questioning agents — this is your crowd.
📍 May 8
📍 NYC (Jane Street offices)
📝 Submit a short extended abstract by April 6: https://t.co/Q73d0n0W7b

More details: https://t.co/BkNi9QDZWj

---
Come meet the people shaping the future of agents.

#AIAgents #AgenticAI #MachineLearning #SystemsResearch #HCI #AIResearch #AcademicTwitter #NYCTech

[Reya Vir @ReyaVir]

Your AI agent doesn't care about your README

It needs commands, local rules, and entry points—not high-level fluff. I wrote about how to automate a hierarchical context map for your codebase in my blog on @gitconnected

Check it out here! https://t.co/IG5NKOUR9Y

[Towards Data Science @TDataScience]

"Vibe-coded mirages are not products, and you shouldn’t trust anyone who says otherwise. They are simply proof-of-concepts for early feedback."

@ReyaVir and @virrahul explain why AI projects so often fail to make it into production (and what you can do about it). https://t.co/f7qMdziAXD

[Towards Data Science @TDataScience]

If you and your company have been swept up in the current vibe-coding wave, Reya Vir's new article is a must-read: it outlines the risks and "security debt" you have to keep in mind as you optimize for speed and quick iteration. https://t.co/3Ji0kjTohB

[DAPLab @DAP__Lab]

🤖 Calling all academic researchers in Agents!

We are excited to announce North East AI Agents Day, a one-day workshop bringing together communities in ML, Systems, and HCI!

📅 May 8th
📍 New York
💡 Submit your extended abstract (DDL: Apr 1st)!

More: https://t.co/eODZzagVjx

[DAPLab @DAP__Lab]

9 Critical Failure Patterns of Coding Agents

Vibe coding feels like magic. Until you try to ship a real feature.

We spent last semester using and evaluating the top AI agents (Claude, Cline, Cursor, Replit) by building 15+ real-world applications.

We collected hundreds of failures and found 9 recurring patterns that repeat across every single tool.

The reality is that agents often prioritize runnable code over correct code. They suppress errors to keep the app "alive," even if the underlying logic is broken.

We documented the critical failure patterns, including:
1) Business Logic Mismatch: Why agents struggle with basic rules (like applying a discount to a shopping cart total).
2) Presentation & UI Grounding Mismatch: Why layouts break because agents can't see.
3) Exception & Error Handling: How agents suppress errors just to make code run.

Read more about it here! https://t.co/xsvDH5pbCl

[DAPLab @DAP__Lab]

Why Vibe Coding Fails and How to Fix It

Everyone is talking about how AI agents will 10x developer productivity.

But anyone who has actually built a real app with Cursor, Cline, or Replit knows the reality:

The first draft looks amazing. But as soon as you try to iterate? The application starts breaking.

This is the struggle of Vibe Debugging.

It starts out looking great. But then you encounter silent errors and buggy logic. You realize the AI doesn't actually understand what you are building, and you are stuck trying to fix a black box.

At Columbia DAPLab, we are investigating exactly why this happens. We have written a blog series on the reality of Vibe Debugging and how to close the gap between demo and production.

Read our first part here! https://t.co/3on1DlaoYd