Reinforcement learning from human feedback (RLHF) is a popular technique for training high-quality AI assistants. However, RLHF may also encourage model responses that match user beliefs over truthful responses, a behavior known as sycophancy. We investigate the prevalence of sycophancy in RLHF-trained models and whether human preference judgments are responsible. We first demonstrate that five state-of-the-art AI assistants consistently exhibit sycophancy behavior across four varied free-form text-generation tasks. To understand if human preferences drive this broadly observed behavior of RLHF models, we analyze existing human preference data. We find that when a response matches a user's views, it is more likely to be preferred. Moreover, both humans and preference models (PMs) prefer convincingly-written sycophantic responses over correct ones a non-negligible fraction of the time. Optimizing model outputs against PMs also sometimes sacrifices truthfulness in favor of sycophancy. Overall, our results indicate that sycophancy is a general behavior of RLHF models, likely driven in part by human preference judgments favoring sycophantic responses.

We investigate a family of simple long-context attacks on large language models: prompting with hundreds of demonstrations of undesirable behavior. This attack is newly feasible with the larger context windows recently deployed by language model providers like Google DeepMind, OpenAI and Anthropic. We find that in diverse, realistic circumstances, the effectiveness of this attack follows a power law, up to hundreds of shots. We demonstrate the success of this attack on the most widely used state-of-the-art closed-weight models, and across various tasks. Our results suggest very long contexts present a rich new attack surface for LLMs.

The reactive paradigm for developing user interfaces promises both simplicity and scalability, but existing frameworks usually compromise one for the other. We present Riffle, a reactive state management system that achieves both simplicity and scalability by managing the entire state of a web application in a client-side persistent relational database. Data transformations over the application state are defined in a graph of reactive relational queries, providing developers with a simple spreadsheet-like reactivity model. Domain state and UI state are unified within the same system, and efficient incremental query maintenance ensures the UI remains responsive. We present a formative case study of using Riffle to build a music management application with complex data and stringent performance requirements.

Recent work shows that the expressive power of Graph Neural Networks (GNNs) in distinguishing non-isomorphic graphs is exactly the same as that of the Weisfeiler-Lehman (WL) graph test. In particular, they show that the WL test can be simulated by GNNs. However, those simulations involve neural networks for the “combine” function of size polynomial or even exponential in the number of graph nodes $n$, as well as feature vectors of length linear in $n$. We present an improved simulation of the WL test on GNNs with {\em exponentially} lower complexity. In particular, the neural network implementing the combine function in each node has only $\mathrm{polylog}(n)$ parameters, and the feature vectors exchanged by the nodes of GNN consists of only $O(\log n)$ bits. We also give logarithmic lower bounds for the feature vector length and the size of the neural networks, showing the (near)-optimality of our construction.

The FoundationDB Record Layer is an open source library that provides a record-oriented data store with semantics similar to a relational database implemented on top of FoundationDB, an ordered, transactional key-value store. The Record Layer provides a lightweight, highly extensible way to store structured data. It offers schema management and a rich set of query and indexing facilities, some of which are not usually found in traditional relational databases, such as nested record types, indexes on commit versions, and indexes that span multiple record types. The Record Layer is stateless and built for massive multi-tenancy, encapsulating and isolating all of a tenant's state, including indexes, into a separate logical database. We demonstrate how the Record Layer is used by CloudKit, Apple's cloud backend service, to provide powerful abstractions to applications serving hundreds of millions of users. CloudKit uses the Record Layer to host billions of independent databases, many with a common schema. Features provided by the Record Layer enable CloudKit to provide richer APIs and stronger semantics with reduced maintenance overhead and improved scalability.

Many sparse matrices and tensors from a variety of applications, such as finite element methods and computational chemistry, have a natural aligned rectangular nonzero block structure. Researchers have designed high-performance blocked sparse operations which can take advantage of this sparsity structure to reduce the complexity of storing the locations of nonzeros. The performance of a blocked sparse operation depends on how well the block size reflects the structure of nonzeros in the tensor. Sparse tensor structure is generally unknown until runtime, so block size selection must be efficient. The fill is a quantity which, for some block size, relates the number of nonzero blocks to the number of nonzeros. Many performance models use the fill to help choose a block size. However, the fill is expensive to compute exactly. We present a sampling-based algorithm called Phil to estimate the fill of sparse matrices and tensors in any format. We provide theoretical guarantees for sparse matrices and tensors, and experimental results for matrices. The existing state-of-the-art fill estimation algorithm, which we will call OSKI, runs in time linear in the number of elements in the tensor. The number of samples Phil needs to compute a fill estimate is unrelated to the number of nonzeros and depends only on the order (number of dimensions) of the tensor, desired accuracy of the estimate, desired probability of achieving this accuracy, and number of considered block sizes. We compare Phil and OSKI on a suite of 42 matrices. On most inputs, Phil estimates the fill at least 2 times faster and often more than 20 times faster than OSKI. Phil consistently produced accurate estimates; in all cases that we tested Phil was faster and/or more accurate than OSKI. Finally, we find that Phil and OSKI produce comparable speedups in multicore blocked sparse matrix-vector multiplication (SpMV) when the block size was chosen using fill estimates in a model due to Vuduc et al.