we moved our whole org off Vercel after that selfie Rauch put out. rotten company, overpriced product for what it is, sneaky practices. never looked back.
yess. loads of space for further exploration here. there is an attempt to keep things as general as possible in the expert.md file, but hard to mitigate overfitting fully. however, changing the seed will not get you much further with all else in the solver constant. unless you try a number of seed that exponentially scales with the size of the problem
sure. in the limit, everything is parameter tuning. with large enough NP-hard problems, the complexity of the search space is big enough that its infeasible to get to a better state by just tuning params in any reasonable amount of time.
as its from 2024 (MaxSAT was not held in 2025), its quite likely all the solvers are in the training data. so the interesting part here is the instances for which we actually got better costs that what is currently known (in the best-cost.csv) file.
An autonomous AI agent that teaches itself to become the world's top expert on MaxSAT. Given weighted MaxSAT instances, it learns novel strategies, finds better solutions and iteratively refines its toolbox. No human guidance.
Ntropy | https://ntropy.network/ | ML & Backend engineers | SF Bay Area / London, UK / Remote | Full-time
Ntropy is building a data layer to combine financial transactions from across organizations in a scalable and privacy-preserving way.
You will be one of the first hires joining the team of 6 (2 founders + 4 engineers). We are well funded and will be scaling up to 10-12 people over the next 4 months.