←
Connor Lawless56 posts
Connor Lawless avatar

Connor Lawless

@LawlessOpt

he/him 🌈 Research at @percepta Prev: @StanfordHAI @CornellORIE @MSFTResearch, @IBMResearch, @uoftmie

◷ Joined January 2021▧ 18 Photos and videos
Connor Lawless avatar
Connor Lawless@LawlessOpt·Nov 11

Insanely excited about Percepta and our vision for Agentic OR! The world is full of scarcity, OR is an amazing tool to help manage scarce resources - let's make sure everyone can use it and can use it well in the age of AI!

Athul Paul Jacob @apjacob03 Nov 10 Article Our Agentic Operations Research Thesis Organizations face thousands of operational decisions daily: which customers to prioritize, where to send staff, which packages to put on the next truck. A hundred years ago, humans made all of these

Chara Podimata avatar
⟳ Connor Lawless retweeted
Chara Podimata@charapod·Oct 23

I've been thinking a lot about AI slop lately, and there are a few thoughts that I wanted to document, not because they are finalized and won’t change, but just in case others find them useful. 1/n

Connor Lawless avatar
Connor Lawless@LawlessOpt·Oct 18

Check out Henry's talk! Really love this project and the doors it opens for doing verifiable and trustworthy optimization with LLMs!

Check out Henry's talk on our upcoming @NeurIPSConf 2026 paper, "FLARE: Verifying MILP Reformulations with LLM-Based Theorem Proving." Paper: arxiv.org/abs/2608.25220 Code + Benchmark: flare.henryrobbins.com Led by Henry, with @LawlessOpt and @madeleineudell, using @leanprover.

Will Ma avatar
⟳ Connor Lawless retweeted
Will Ma@willma353·Oct 16

I’m a Lion King fanatic, karaoke bar pianist, and researcher in AI decision-making. This was inevitable. “Can You Feel the AGI?” Original in the reply below.

2:46
Eugene Vinitsky 🦋 avatar
⟳ Connor Lawless retweeted
Eugene Vinitsky 🦋@EugeneVinitsky·Oct 7

I'm hiring for our interpretable world modeling effort at Percepta! The core question: how can we make an agent build a simulator, understand a company, and then design a policy, all from unstructured data? Come work with me and our amazing team. jobs.ashbyhq.com/percepta/90…

Christos Tzamos avatar
⟳ Connor Lawless retweeted
Christos Tzamos@ChristosTzamos·Oct 2

Neo in the Matrix, learns Kung-Fu without "training" by getting the skill uploaded to his brain. Our new architecture, Spotlight, enables LLMs to grow and gain new capabilities without changing their weights. Check out our work!

1/ What would it take for LLMs to be able to grow their own capabilities? We introduce spotlight, a memory architecture with growing capacity but with linear computational complexity. We show that this suffices to host evolving ecosystems like software by building Python directly into an LLM. We also share some very early language modeling results where it outperforms attention and linear attention on long context capabilities!

0:08
Athul Paul Jacob avatar
⟳ Connor Lawless retweeted
Athul Paul Jacob@apjacob03·Oct 2

1/ What would it take for LLMs to be able to grow their own capabilities? We introduce spotlight, a memory architecture with growing capacity but with linear computational complexity. We show that this suffices to host evolving ecosystems like software by building Python directly into an LLM. We also share some very early language modeling results where it outperforms attention and linear attention on long context capabilities!

0:08
Angela Zhou avatar
⟳ Connor Lawless retweeted
Angela Zhou@angelamczhou·Sep 16

We can't let frontier labs choose their own auditors - or their own questions.

Post attachment
Connor Lawless avatar
Connor Lawless@LawlessOpt·Sep 1

Super excited about this paper led by the incomparable Henry Robbins! You no longer need heuristics to check that your LLM correctly reformulated a MILP problem (or passes a benchmark), we can prove it in Lean for any instance!

An LLM can rewrite your optimization problem to improve solve time, pass every test, and still silently change the underlying problem. Our new paper introduces FLARE, an LLM agent that uses Lean to prove that a given MILP reformulation is valid across all possible problem instances, not just those used for testing. On 54 reformulation pairs of NP-hard problems, FLARE correctly classified all (best baseline: 83%) and provided a machine-checkable proof for every accepted reformulation. AI-generated optimization needs proofs; passing tests isn’t enough.

Post attachment
Hirsh Jain avatar
⟳ Connor Lawless retweeted
Hirsh Jain@hirshjain·Aug 19

It's very easy to arm-chair quarterback healthcare transformation from an office in San Francisco. Much harder to actually assemble the avengers in Akron Ohio and try to fix it. Very proud of the role @percepta plays in this work. Reach out if you want to get on the ground in Akron with our team

In 2024, we made the unprecedented decision to acquire a hospital system. It was an opportunity to create a blueprint for healthcare transformation to make American healthcare proactive, accessible, and affordable. @SummaHealth and our Health Assurance Transformation Company (HATCo) revealed their technology transformation stack, partnering with some of our portfolio companies @aidocmed, Clarium, @CommureOs, @poweredbyfabric, @hippocraticai, @judihealth, @transcarent, and @versemedical. @percepta is serving as a transformation partner, unifying the tech stack into a seamless Al-native operating system. We believe the future of healthcare is health assurance with tech founders and health system leaders working together to reimagine healthcare in the US and beyond.

0:40
Ellen Vitercik avatar
⟳ Connor Lawless retweeted
Ellen Vitercik@vitercik·Jan 19

@LawlessOpt and I are excited to present our #AAAI2026 tutorial on “LLMs for Optimization: Modeling, Solving, and Validating with Generative AI.” When: Tuesday, Jan 20, 2026, 8:30am–12:30pm (Singapore time) Where: Garnet 216 (Singapore EXPO) Optimization is central to planning, scheduling, and decision-making, but deploying solvers requires deep expertise. Our tutorial covers how LLMs can support the end-to-end optimization pipeline (model formulation, solver configuration, and model validation) and highlights open research directions. Tutorial page (agenda + reading list): conlaw.github.io/llm_opt_tut… (Connor’s intro slides are shown here.) Thanks to @leo_bix and @madeleineudell for helping put the proposal together. CC @RealAAAI

Post attachmentPost attachmentPost attachmentPost attachment
Connor Lawless avatar
Connor Lawless@LawlessOpt·21 Oct 2024

Excited to be talking about this project at INFORMS today (ME31 - 4:00 @ Summit 422)! In this paper we build and do the first user study with a system that combines LLMs with Constraint Programming for personalized optimization modelling (accepted in ACM TiiS, an HCI journal!)

Super excited about this project from my time at @MSFTResearch! We explore how to combine LLMs and Constraint Programming to allow non-expert users to design optimization models in the context of meeting scheduling.

Thiago Serra (@thserra.bsky.social) avatar
⟳ Connor Lawless retweeted
Thiago Serra (@thserra.bsky.social)@thserra·29 May 2024

Connor Lawless (@LawlessOpt) talks at #cpaior2024 about a new notion of fairness in clustering to ensure minimum majority representation of groups across clusters, which helps shaping more representative electoral districts, & which may shown to be impossible by an exact approach

Post attachmentPost attachmentPost attachmentPost attachment