
Natacha Crooks
@siobhcroo
Assistant Professor at UC Berkeley. Distributed Systems & databases. Former engineer at Materialize. PhD UT Austin. Originally from Paris, France. Views my own.
ID: 219600575
25-11-2010 09:42:27
1,1K Tweet
3,3K Followers
617 Following



Awesome to see our new consensus protocol Autobahn having impact in industry! (@ this year's SOSP: arxiv.org/abs/2401.10369) Excited to see Somnia power Improbable's Msquared : somnia.network/somnia-s-data-… PS: Hire Florian, Neil, the brains behind Autobahn! Ittai Abraham Florian Suri-Payer

The next SF Systems Meetup is coming up! Talks will be Alex Krentsel on software-defined networking and Peter Kraft and Qian Li on Transactions in Serverless! Register here lu.ma/lhuuiur5 and check out sfsystemsclub.com for more details.

Neil Giridharan from UC Berkeley EECS presented Autobahn, a high-throughput BFT protocol that offers both low latency and seamless recovery (from events that interrupt progress) at @IllinoisCDS Systems Research Seminar. The work is published at SOSP '24, dl.acm.org/doi/10.1145/36…




I am disappointed to see that Brown no longer requires me to rate the artistic ability of the people I am recommending me for PhD admissions in CS. I was enjoying the mandatory tap dancing interview prior to agreeing to write them a letter Computer Systems and Networks @ Brown.



A poodle, a latte, California sun and Andy Pavlo (@andypavlo.bsky.social)'s new query optimizer lecture course. Not a bad start to a Saturday morning walk.

Very grateful to be part of the 2025 Sloan Research Fellow cohorts (and in the company of the amazing Raul Castro Fernandez!). Thank you my fantastic students and amazing colleagues who have made this possible! Many of them will be graduating soon. Hire them!

Massive shoutout to Neil Giridharan, Florian Suri-Payer, Ittai Abraham, Lorenzo Alvisi, and Natacha Crooks for their insightful work on Autobahn (which heavily inspired the design of broadcast::linked) 🙇

Many federal-funded success stories in the data systems universe that I’m aware of, including Google (2+ T) - from Stanford - and Databricks (60B) from UC Berkeley EECS. Any of these would pay for the costs (eg all of NSF: 10B in total per year) many times over. Cost cutting in