arXiv subjects

Jakub Smékal

Publications and source records attributed to Jakub Smékal.

4 recordsLinked to original sources

arXiv2026

Can your AI agent be cheaper? Investigating the effects of task specifications on token spend in agentic coding tasks

Agentic coding workflows are now widely deployed in real-world systems. With long-horizon reasoning and tool use, token usage has become an important consideration for both cost and efficiency. Two engineers using AI will solve the same problem differently. How the specification of a task shapes an agent's token spend, and whether that spend can be predicted in advance, are open questions. Here, we study the effects of different task specifications on agentic token spend with the Kimi K3 model at three thinking efforts. Across $2,700$ runs, we show that reducing a full task specification to a bare user story raises token spend by $29.7\%$, while run-to-run variance remains unaffected by any prompt changes. We show that prompt-sensitivity is task-dependent, running from $13\%$ to $115\%$. We fit a simple predictor that can price a full distribution of task specifications and thinking effort configurations from a single cheap probe on an unseen task within $36\%$, improving over prior work in predicting token spend. Our work provides initial results quantifying the effects of task specification on agentic token spend and introduces a method that can be used to systematically evaluate the cost of AI coding workflows.

cs.AI↗

arXiv2024

Towards a theory of learning dynamics in deep state space models

State space models (SSMs) have shown remarkable empirical performance on many long sequence modeling tasks, but a theoretical understanding of these models is still lacking. In this work, we study the learning dynamics of linear SSMs to understand how covariance structure in data, latent state size, and initialization affect the evolution of parameters throughout learning with gradient descent. We show that focusing on the learning dynamics in the frequency domain affords analytical solutions under mild assumptions, and we establish a link between one-dimensional SSMs and the dynamics of deep linear feed-forward networks. Finally, we analyze how latent state over-parameterization affects convergence time and describe future work in extending our results to the study of deep SSMs with nonlinear connections. This work is a step toward a theory of learning dynamics in deep state space models.

cs.LG↗

arXiv2023

Decentralized Technologies for AI Hubs

AI requires heavy amounts of storage and compute with assets that are commonly stored in AI Hubs. AI Hubs have contributed significantly to the democratization of AI. However, existing implementations are associated with certain benefits and limitations that stem from the underlying infrastructure and governance systems with which they are built. These limitations include high costs, lack of monetization and reward, lack of control and difficulty of reproducibility. In the current work, we explore the potential of decentralized technologies - such as Web3 wallets, peer-to-peer marketplaces, storage and compute, and DAOs - to address some of these issues. We suggest that these infrastructural components can be used in combination in the design and construction of decentralized AI Hubs.

cs.AI↗

arXiv2022

Libraries, Integrations and Hubs for Decentralized AI using IPFS

AI requires heavy amounts of storage and compute. As a result, AI developers are regular users of centralised cloud services such as AWS, GCP and Azure, compute environments such as Jupyter and Colab notebooks, and AI Hubs such as HuggingFace and ActiveLoop. There services are associated with certain benefits and limitations that stem from the underlying infrastructure and governance systems with which they are built. These limitations include high costs, lack of monetization and reward, lack of control and difficulty of reproducibility. At the same time, there are few libraries that allow data scientists to interact with decentralised storage in the language that data scientists are used to, and few hubs where they can discover and interact with AI assets. In this report, we explore the potential of decentralized technologies - such as Web3 wallets, peer-to-peer marketplaces, decentralized storage (IPFS and Filecoin) and compute, and DAOs - to address some of the above limitations. We showcase some of the libraries and integrations that we have built to tackle these issues, as well as a proof of concept of a decentralized AI Hub app, that all use IPFS as a core infrastructural component.

cs.NI↗