August Meetup

Schedule

• AI coding benchmarks with SWE-Bench
• Overview on CAN Protocol
• AI Agents in Parsing PDF
• Lightning talks.

Summary

AI coding benchmarks with SWE-Bench

Speaker: Abhishek

SWE-Bench is a popular benchmarking system that tests an AI system's ability to solve Github issues. In the talk we'll go over some of the issues that the benchmark includes and how it verifies the solutions submitted by AI systems. We'll also review few of the top AI-systems on the leaderboard (Trae, Openhands, Warp etc), and see what all techniques they use to solve the issues.

Overview of CAN protocol

Speaker: Praveen

In this talk, the history and concepts of CAN protocol with some real world usage are discussed along with code level implementation using Python. At the end of the session , a simple GUI based vehicle simulation demo is shown with gaming elements

AI Agents in Parsing PDF

Speaker: Arokyiaraj

AI agents with example of parsing complex PDF. With some experience I have learnt to improve the accuracy of the PDF data extraction.

Talk at Chennaipy

We have three 20 mins talk slots. The talks are filled by first come first serve basis. Lightning talks will be at the end of the meetup. As long as we have time, there is no limit for number of lightning talks.
If you are interested in doing a talk (20 min) or lightning talk (5 mins), please add a comment to this event page with your topic and Description.

Note:
We understand that your schedule might change and you are unable to attend the meetup, in that case consider UNRSVP. So that folks in waiting list will get a chance to attend the meetup.