ACM SIGOPS

Official account of ACM Special Interest Group in OPerating Systems (SIGOPS) managed by the team at

[ACM SIGOPS @ACMSIGOPS]

New SIGOPS Blog -- "Can LLMs model real-world systems in TLA+?" by Qian Cheng, Ruize Tang, Emilie Ma, Finn Hackett, Peiyang He, Yiming Su, Ivan Beschastnikh, Yu Huang, Xiaoxing Ma, and Tianyin Xu.
https://t.co/nCEUg3zFV2

[ACM SIGOPS @ACMSIGOPS]

New SIGOPS Blog -- "The Long Game: How Agents That Remember Resolve Operational Issues Faster" by Shihang (Vic) Li, Thomas Anderson, Ratul Mahajan, Simon Peter, Luke Zettlemoyer, and the SDS team.
https://t.co/mjYKGKWRf9

[ACM SIGOPS @ACMSIGOPS]

New SIGOPS Blog -- "LDOS: Toward A Learning-Directed Operating System" by by Divyanshu Saxena, Aneesh Durg, Sujay Yadalam, Jane Chen, Rohit Dwivedula, Chris Rossbach, and Aditya Akella.

https://t.co/GmbIaZLybs

[ACM SIGOPS @ACMSIGOPS]

New SIGOPS Blog -- "Let the Barbarians In: How AI Can Accelerate Systems Performance Research" by @ai4research_ucb
https://t.co/ekXftmkaJ0

[CACM Editor @blogCACM]

How Over-Engineering Became the New Technical Debt in Distributed Systems

Over-engineered systems evolve through a series of reasonable decisions that can reflect past fears rather than current needs. https://t.co/bAOYCRzUgA

[Tianyin Xu @tianyin_xu]

Great work from the Glia team led by Mohammad and Hari (@HariBalakrish20) at @MITCSAIL and @MITEECS.

The @SysIntelligenc team was defining the ladder of system intelligence based on the training process of PhD students in the last @ACMSIGOPS blog, and now we have Glia as a PhD-level AI for system design and optimization.

[ACM SIGOPS @ACMSIGOPS]

New SIGOPS Blog -- Glia: A Human-Inspired AI for Systems Design and Optimization from @MIT_CSAIL.
https://t.co/ailmyFtCfb

Glia is a PhD-level AI designed to autonomously architect and continuously optimize complex systems infrastructures.

@MITEECS @MIT

[Tianyin Xu @tianyin_xu]

This's an incredibly exciting effort led by @FelxFeng with many colleagues @MSFTResearch and some of us @siebelschool. I truly believe AI can learn all the essential system capabilities and evolve into the envisioned System Intelligence.

But, this vision requires the entire system community to enable -- we need to teach AI how to think, reason, build, operate "systems" as how we teach our own graduate students and help them grow into systems researchers. AIs are great learners, but we are not great teachers for them yet.

[System Intelligence @SysIntelligenc]

I’m excited to introduce the System Intelligence project which aims to build a future where advanced AI can design, implement, and operate next-generation computing systems. To realize this vision, we must unlock AI's next stage of capabilities – reasoning about architectures and protocols, weighing tradeoffs, applying enduring principles, developing effective abstractions, and more – beyond coding and bug fixing.

We share our efforts on defining System Intelligence and our perspective on how to realize it in a recent SIGOPS Blog (https://t.co/NQkT1GhFnf). We regard benchmarks as an initial foundation, and have been developing a System Intelligence Benchmark.

We’d love to hear your feedback and look forward to your contributions!

🌐 Website: https://t.co/I0WzuJXRb6
🛠️ GitHub: https://t.co/piM8eCQiT9!

[ACM SIGOPS @ACMSIGOPS]

New @ACMSIGOPS Blog cross-referencing @sigarch :

From Theory to Practice: Introducing Architectural Prisms, an Experiment in AI-First Academic Dialogue

https://t.co/K68ZTMZhDx

[Tianyin Xu @tianyin_xu]

This is a long overdue. If you are interested in Rex kernel extensions (https://t.co/44SMsWqjfx), @Jinghao_J gave a great talk at #OSS early this year.

The talk can be found here,
https://t.co/zbPykyqcq1

[Tianyin Xu @tianyin_xu]

Jinghao (@Jinghao_J) gave a great remote guest lecture on Safe Kernel Extensions at CS 423 today, teaching eBPF and Rex. It's always special to have him in 423 which he put his heart in as a distinguished TA in the past 5 years. I captured his slide on Rex, which is the system we use for MP4 and is his own PhD thesis.

The Rex project: https://t.co/B2CZSwibIS

[Tianyin Xu @tianyin_xu]

This's a brilliant article written by @luo_mai's team @EdinburghUni and @fanyang's team @MSFTResearch. It's a must to read for anyone interested in future AI hardware.

Wafer-scale chips are exciting. Today's AI software stack falls short in exploiting them to realize wafer-scale systems.

[ACM SIGOPS @ACMSIGOPS]

Wafer-Scale AI Compute: A System Software Perspective.

New @ACMSIGOPS Blog at https://t.co/XSVZAhANpc

[ACM SIGOPS @ACMSIGOPS]

Barbarians at The Gate: How AI is Upending Systems Research by @audreyccheng, @LynnLiu41887950, @melissapan, @istoica05, and the @ai4research_ucb team,
https://t.co/b6vtMJN3Et

This's first article of the The Next Horizon of System Intelligence blog series.

[ACM SIGOPS @ACMSIGOPS]

A cross-posted article from @sigarch on "Ethical and Moral Fraying due to Intellectual Conflicts in Paper Reviews" by T. N. Vijaykumar at SIGOPS Blog.
https://t.co/pvXtSOevSh

[ACM SIGOPS @ACMSIGOPS]

Read the Five Years of Artifact Evaluation at EuroSys on SIGOPS Blog,
https://t.co/H20qSOo0fs

[Disseminate: The Computer Science Research Podcast @DisseminatePod]

🚨 "Lessons Learned from Five Years of Artifact Evaluations at EuroSys" with Thaleia Doudali (@ThaleiaDimitra), Miguel Matos, and Anjo Vahldiek-Oberwagner (@ovahldy) is available now!

🎧 Listen on Apple ➡️ https://t.co/02zfDQ6ggq

🎧 Listen on Spotify ➡️ https://t.co/05qq7w4ElY

[Disseminate: The Computer Science Research Podcast @DisseminatePod]

🚨 "Lessons Learned from Five Years of Artifact Evaluations at EuroSys" with Thaleia Doudali (@ThaleiaDimitra), Miguel Matos, and Anjo Vahldiek-Oberwagner (@ovahldy) is available now!

🎧 Listen on Apple ➡️ https://t.co/02zfDQ6ggq

🎧 Listen on Spotify ➡️ https://t.co/05qq7w4ElY

[ACM SIGOPS @ACMSIGOPS]

We also published the article at @ACMSIGOPS Blog!
https://t.co/1b1b17hGw5

[Vijay Chidambaram @vijay_ut]

[new blog post]

I wrote a blog post in the @sigarch blog about how I think LLMs should be used for writing and reviewing papers

https://t.co/5GlermylKE

Quick summary: I think we should legalize the use of LLMs and regulate and guide authors and reviewers about how to use them

[ACM SIGOPS @ACMSIGOPS]

The Academic Pipeline Stall: Why Industry Must Stand for Academia, by Professor Vijay Janapa Reddi.

https://t.co/jDnj28lixP