Software development is shifting from traditional programming to AI-integrated applications that leverage generative AI and large language models (LLMs) during runtime. However, integrating LLMs remains complex, requiring developers to manually craft prompts and process outputs. Existing tools attempt to assist with prompt engineering, but often introduce additional complexity. This paper presents Meaning-Typed Programming (MTP) , a novel paradigm that abstracts LLM integration through intuitive language-level constructs. By leveraging the inherent semantic richness of code, MTP automates prompt generation and response handling without additional developer effort. We introduce the (1) by operator for seamless LLM invocation, (2) MT-IR , a meaning-based intermediate representation for semantic extraction, and (3) MT-Runtime , an automated system for managing LLM interactions. We implement MTP in Jac , a programming language that supersets Python, and find that MTP significantly reduces coding complexity while maintaining accuracy and efficiency. MTP significantly reduces development complexity, lines of code modifications needed, and costs while improving run-time performance and maintaining or exceeding the accuracy of existing approaches. Our user study shows that developers using MTP completed tasks 3.2× faster with 45% fewer lines of code compared to existing frameworks. Moreover, MTP demonstrates resilience even when up to 50% of naming conventions are degraded, demonstrating robustness to suboptimal code. MTP is developed as part of the Jaseci open-source project, and is available under the module byLLM .

Many companies use large language models (LLMs) offered as a service, like OpenAl's GPT-4, to create AI-enabled product experiences. Along with the benefits of ease-of-use and shortened time-to-solution, this reliance on proprietary services has downsides in model control, performance reliability, uptime predictability, and cost. At the same time, a flurry of open-source small language models (SLMs) has been made avail-able for commercial use. However, their readiness to replace existing capabilities remains unclear, and a systematic approach to holistically evaluate these SLMs is not readily available. This paper presents a systematic evaluation methodology and a characterization of modern open-source SLMs and their trade-offs when replacing proprietary LLMs for a real-world product feature. We have designed SLaM, an open-source automated analysis tool that enables the quantitative and qualitative testing of product features utilizing arbitrary SLMs. Using SLaM, we examine the quality and performance characteristics of modern SLMs relative to an existing customer-facing implementation using the OpenAI GPT-4 API. Across 9 SLMs and their 29 variants, we observe that SLMs provide competitive results, significant performance consistency improvements, and a cost reduction of 5xrv29x when compared to GPT-4.

This paper explores the possibility of improving human haptic capabilities by amplifying minute surface texture irregularities that are otherwise undetectable to the human touch. The study was carried out with different controllers for surface texture reproduction and amplification aiming for enhanced haptic perception. Firstly, a non-identical master replica system that is capable of simultaneous force-position response amplification was developed. The robust control was realized with the disturbance observer. Three different controllers; a position controller, a force controller, and an acceleration-based scaling bilateral controller were applied. The results confirm that the rearmost controller successfully reproduced amplified haptic feedback of surface texture at the master despite the inherent vibration and noises introduced due to the lateral movement of the surface. The data extracted from the surfaces using the scaling bilateral controller demonstrate unique properties per object that can be applied for object classification.