Mark Müller (@mnmueller) profile picture

Co-founder and CTO at https://xitter.cf/t.co/l2sBCoRD0j. Working on monitoring and self-improvement for Software Factories. ML PhD from @the_sri_lab at @ETHZ

Zurich
Joined January 2021
Photo by Mark Müller (@mnmueller)Photo by Mark Müller (@mnmueller)Photo by Mark Müller (@mnmueller)Photo by Mark Müller (@mnmueller)Photo by Mark Müller (@mnmueller)Photo by Mark Müller (@mnmueller)Photo by Mark Müller (@mnmueller)Photo by Mark Müller (@mnmueller)
Mark Müller retweeted
Did we just blow our entire marketing budget on this sign at AI Council? 🤔 Come find our CTO @mnmueller in SF this week to hear what we're building at LogicStar. And to confirm whether we have any runway left.
🤖 Made with AI
2
2
462
Mark Müller retweeted
Lazar Kanelov will demonstrate how high-quality telemetry data powers AI-driven incident response, creating adaptive feedback loops where agents interpret system signals, identify root causes, and apply automated remediation. RSVP ➡️ meetup.com/localstack-commun…
2
2
250
Mark Müller retweeted
Stop fixing bugs. Let AI Agents fix them for you. Join us for a session on Autonomous Software Systems and learn how AI agents are using telemetry data to detect, diagnose, and fix production bugs without human intervention. meetup.com/localstack-commun…
1
3
9
469
Mark Müller retweeted
Great dinner with @lovable, @localstack, and @logic_star_ai AI (three “Lo*”s) in Zurich - discussing the future of agentic coding 🤖, cloud DevX 💻, and building delightful apps ✨. Can't wait for more collaborations and partnerships among the three “Lo*”s and beyond! 🚀
4
5
371
We are excited to see the community use our SWT-Bench and work on the crucial topic of test generation!
🚨 New SWT-Bench Submission! 🤖 Amazon Q Developer Agent leads the SWT-Bench leaderboard 🥇 with an impressive 49% of successfully tested issues and a coverage improvement of 57% on SWT-Bench Verified.
2
5
203
SOTA code agent OpenHands (top-1 for SWE-full) achieves only 22% accuracy in unit test generation on SWT-lite (half its SWE performance), only slightly outperforming SWE-agent. What is going on? We dug through the data to find a simple trick and achieve almost 30%! 👇🧵 1/9
1
2
5
272
We have our first submission for SWT-Bench 🚀 AEGIS, a dedicated test generation agent, achieves 47.8% accuracy 🏆 , significantly outperforming our SWE-Agent+ baseline and demonstrating the potential of dedicated test generation agents. 1/3 🧵
2
4
1
7
862
Exiting to see our work on benchmarking the test-generation capabilities of LLMs being picked up by the community!
Super cool work by @nielstron et al: SWT-Bench is SWE-bench for test generation! They give the model a repo and an issue and it has to write a test for the issue. They show that SWE-agent is able to write good tests for 19% of the issues in the benchmark! 🧵(1/3)
1
2
76
Presenting today @icmlconf 2024 Workshop FM in the Wild 🤖 🏞️ "Code Agents are State of The Art Software Testers" SWE-Agent, aider and co are competent at reproducing GitHub issues, performing as well as specialized methods. Looking forward to answer your questions!
1
4
12
1,082
On Tuesday at 11:30, in Poster Session 1, we will present Prompt Sketching, a novel decoder-driven approach for templated (and constrained) text generation of LLMs. 📄 arxiv.org/abs/2311.04954 👨‍💻 Work with @mnmueller, @lbeurerkellner, @mvechev.
1
1
4
52
Mark Müller retweeted
A couple of amazing PhD students graduated from our lab (@the_sri_lab) at ETH Zurich today: @mbalunovic and @mnmueller. Both did fantastic contributions to the area of Safe and Secure AI: impactful papers and systems the community built upon. Next steps should be exciting :)
1
4
39
1,969
Mark Müller retweeted
Find us @NeurIPSConf #NeurIPS2023 to chat about our latest work. We are excited to share works on certified robustness, a large scale study of image classifiers, and game theory. All works are supervised by @mvechev. 🧵
1
3
8
881
Mark Müller retweeted
@mnmueller and @marc_r_fischer introduced a new from of Abstract Interpretation for challenging unbounded loops enabling the analysis of fixpoint-based neural network architecture (monDEQs). 🌐 sri.inf.ethz.ch/publications… 📄 arxiv.org/abs/2110.08260 🧵 3/3
1
3
150
Mark Müller retweeted
At @iclr_conf members of SRI lab presented 3 works: - ⚖️ Human-Guided Fair Classification for NLP - 📈 Robustness Verification & Training of Neural ODEs - 📦 Certified Training: Small Boxes are All You Need Find us around the workshops! 🧵 1/4
1
2
5
581
Mark Müller retweeted
📦🚀 Want to know why small boxes are all you need to achieve SOTA in certified robustness? Come to our @iclr_conf spotlight talk (at 16:00 in AD10) or meet us at the poster session after (starting at 16:30). #ICLR2023 #ICLR
2
1
8
986
Mark Müller retweeted
📈 Are Neural ODEs more (provably) robust than standard convolutional architectures? Find out today in Poster Session 3 (11:30) at @iclr_conf where we present our work on "Efficient Certified Training and Robustness Verification of Neural ODEs". #ICLR2023 #ICLR
1
1
3
516
Excited to talk about @lmqllang? @mnmueller and I will be at @iclr_conf and are happy to chat. We will be wearing these stylish shirts to help you find us. #iclr #ICLR2023
3
1
15
1,576
🚀 Excited to announce the first release of lmql.ai, a novel open source programming language and platform for language model interaction! Combining prompts, constraints & scripting, LMQL elevates the capabilities of large language models. 🧵1/6 A quick tour.
14
172
41
725
199,159