@codesweep

Rishi Vaish

@codesweep

Building an autopilot for enterprise software maintenance.

Joined August 2025

About

Nothing here yet.

Available for

Nothing here yet.

Rishi Vaish's blogs

CodeSweep Blogblog.codesweep.ai3 posts

Articles Comments

Recently published

RVRishi Vaishblog.codesweep.aiMay 31 · 11 min read

Why Most Enterprise Software Isn't Ready for Agentic AI

Learnings From the Trenches Every enterprise software company is asking some version of the same question: How do we use AI agents to ship faster and unlock new customer value without putting our miss

RVRishi Vaishblog.codesweep.aiDec 9, 2025 · 5 min read

Mixture of Open-Weight Models with Iterative Patch Generation Improves Performance on SWE-bench

Goal Our goal in this study was to explore whether a mixture of open-weight models, combined through an iterative process, can outperform any single model on the SWE-bench Verified benchmark. Specifically, we wanted to evaluate if patches generated b...

RVRishi Vaishblog.codesweep.aiAug 5, 2025 · 6 min read

Analysis of Reasoning Trajectories - Comparing Closed Weight Models vs Open Weight Models - Claude Sonnet 4 vs Kimi K2 Instruct

Abstract This study presents a comprehensive analysis of SWE-agent trajectories comparing Kimi K2 Instruct and Claude Sonnet 4 performance on software engineering tasks from the SWE-bench dataset. Through detailed examination of action category distr...

Rishi Vaish

About

Available for

Rishi Vaish's blogs

Recently published

Why Most Enterprise Software Isn't Ready for Agentic AI

Mixture of Open-Weight Models with Iterative Patch Generation Improves Performance on SWE-bench

Analysis of Reasoning Trajectories - Comparing Closed Weight Models vs Open Weight Models - Claude Sonnet 4 vs Kimi K2 Instruct

Search Hashnode

Rishi Vaish

About

Available for

Rishi Vaish's blogs

Recently published

Why Most Enterprise Software Isn't Ready for Agentic AI

Mixture of Open-Weight Models with Iterative Patch Generation Improves Performance on SWE-bench

Analysis of Reasoning Trajectories - Comparing Closed Weight Models vs Open Weight Models - Claude Sonnet 4 vs Kimi K2 Instruct