@kolovskydev@tianyin_xu Also, after the agent submits its fix, the env continues to run with the flooder for a specific time window. If the agent had simply done a restart, the flooder would flood enough connections during this window to cause the error to show up again, and the oracle would fail it.
It was a transformative learning experience for me. I got introduced to so many great ideas!
I am grateful to @tianyin_xu for the opportunity and mentorship. Hope to have the opportunity to contribute more in the future!
This post is long overdue, which I owe to the students from the UIUC++ SRSE program. We finally wrote a blog on how we curated a set of high-quality SRE benchmark problems by turning real-world postmortem reports into reproducible SRE problems atop #SREGym. It may give a good example of community-based data curation. Check it out,
https://t.co/vCLXrf87Zk
The fundamental challenge of AI-for-SRE benchmarks is the quality of the problems, e.g., in terms of realism and the ability of challenging frontier AI. This experience enabled us to understand many faces of the challenge and reflect on important tradeoffs between realism, reproducibility, cost, and utility. We learned many lessons, which would guide the effort on building #SREGym 2.0.
Big thanks to @SaadMRP who (unexpectedly) spent his entire summer managing the program with a heroic effort.
I list all the student contributors at the end of the post. Many of them are on Twitter: @12_AbdAllAh_12@ermiasmulu19@sharq_fr@M_ABDz_@MunimThahmid@Sai_Hari_g@ibnAmjid@SuMaya971503@TalhaAsif25@tanzimhromel@tejaspkshukla@Varunihk. They did great work to achieve high-quality problems that challenge AI frontier. If you're looking for students or employees, they are good candidates!
Our team could not qualify for Round 4 of the Adobe University Hackathon 2026.
Nonetheless, we got to learn about agent skills in Round 3. We wrote agent skills for auditing a given url for AI brand visibility and suggesting improvements.
Repo link: https://t.co/3r2I2cBZ1o
You got 2 offers:
Google India - ₹55 LPA
- Office in Bangalore
- 9 to 6 culture
- Brand on resume forever
Zepto - ₹38 LPA
- Fully remote
- Ownership of a full system
- ESOP with real upside
Which one would you choose?