v0.7.0
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cpp11 min read
Alignment Research Center (ARC)
Stay updated with the latest developments in Artificial Intelligence
Agents on live hardware: reason where you must, engineer everywhere else
CoreWeave Blog10 min read
b11669
llama.cpp1 min read
A Mike's-Eye View of ARC's Research
Over the past 15 months or so, ARC's technical agenda has developed quite a bit. The advent of the Matching Sampling Principle (MSP), and ideas like it, has begotten a host of concrete technical problems; progress on those problems has given us more philosophical clarity on the big
Alignment Research Center (ARC)20 min readAnnouncing the ARC White-Box Estimation Challenge
ARC has teamed up with AIcrowd to launch the ARC White-Box Estimation Challenge, a contest to improve upon our estimation algorithms for random MLPs. The warm-up round begins this week, and later rounds will have a total prize pool of at least $100,000. We are very
Alignment Research Center (ARC)4 min readMechanistic estimation for expectations of random products
We have developed some relatively general methods for mechanistic estimation competitive with sampling by studying problems that are expressible as expectations of random products.
Alignment Research Center (ARC)9 min readMechanistic estimation for wide random MLPs
This post covers joint work with Wilson Wu, George Robinson, Mike Winer, Victor Lecomte and Paul Christiano. Thanks to Geoffrey Irving and Jess Riedel for comments on the post.
Alignment Research Center (ARC)8 min readAlgZoo: uninterpreted models with fewer than 1,500 parameters
This post covers work done by several researchers at, visitors to and collaborators of ARC, including Zihao Chen, George Robinson, David Matolcsi, Jacob Stavrianos, Jiawei Li and Michael Sklar. Thanks to Aryan Bhatt, Gabriel Wu, Jiawei Li, Lee Sharkey, Victor Lecomte and Zihao Chen for comments.
Alignment Research Center (ARC)17 min readCompeting with sampling
In 2025, ARC has been making conceptual and theoretical progress at the fastest pace that I've seen since I first interned in 2022. Most of this progress has come about because of a re-orientation around a more specific goal: outperforming random sampling when it comes to understanding
Alignment Research Center (ARC)46 min readObstacles in ARC's research agenda
Former ARC researcher David Matolcsi has put together a sequence of posts that explores ARC's big-picture vision for our research and examines several obstacles that we face. We think these posts will be useful to readers who are interested in digging into the details of our big-
Alignment Research Center (ARC)1 min readA computational no-coincidence principle
In a recent paper in Annals of Mathematics and Philosophy, Fields medalist Timothy Gowers asks why mathematicians sometimes believe that unproved statements are likely to be true.
Alignment Research Center (ARC)12 min readA bird's eye view of ARC's research
Over the last few months, ARC has released a number of pieces of research. While some of these can be independently motivated, there is also a more unified research vision behind them. The purpose of this post is to try to convey some of that vision and how our individual
Alignment Research Center (ARC)9 min readLow Probability Estimation in Language Models
ARC recently released our first empirical paper: Estimating the Probabilities of Rare Language Model Outputs. In this work, we construct a simple setting for low probability estimation — single-token argmax sampling in transformers — and use it to compare the performance of various estimation…
Alignment Research Center (ARC)15 min readResearch update: Towards a Law of Iterated Expectations for Heuristic Estimators
Last week, ARC released a paper called Towards a Law of Iterated Expectations for Heuristic Estimators, which follows up on previous work on formalizing the presumption of independence. Most of the work described here was done in 2023. A brief table of contents for this post: What is a heuristic
Alignment Research Center (ARC)36 min readEstimating Tail Risk in Neural Networks
Machine learning systems are typically trained to maximize average-case performance. However, this method of training can fail to meaningfully control the probability of tail events that might cause significant harm.
Alignment Research Center (ARC)33 min readBackdoors as an analogy for deceptive alignment
ARC has released a paper on Backdoor defense, learnability and obfuscation in which we study a formal notion of backdoors in ML models. Part of our motivation for this is an analogy between backdoors and deceptive alignment, the possibility that an AI system would intentionally behave well in…
Alignment Research Center (ARC)12 min readFormal verification, heuristic explanations and surprise accounting
ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understanding of what was going on inside a neural network, we would hope to be able to use that understanding to verify that the network was
Alignment Research Center (ARC)12 min readMatrix completion prize results
Earlier this year ARC posted a prize for two matrix completion problems. We received a number of submissions we considered useful, but not any complete solutions. We are closing the contest and awarding the following partial prizes:$500 to Elad Hazan for solving a related problem and pointing us
Alignment Research Center (ARC)3 min read
Showing 15 of 15 stories
You're all caught up.
AiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from Alignment Research Center (ARC)
Join 15,000+ AI enthusiasts