DSPy
PulseAugur coverage of DSPy — every cluster mentioning DSPy across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
DSPy framework applies OOP principles to LLM prompt engineering
The DSPy framework, developed at Stanford University, introduces an object-oriented approach to prompt engineering for large language models. It separates the stable interface, or 'Signature,' from the implementation de…
-
GEPA method optimizes LLM prompts using AI critiques, no GPU needed
A new method called GEPA (Genetic-Pareto Evolutionary Prompt Adaptation) has been introduced, aiming to optimize LLM pipelines without requiring extensive GPU resources for fine-tuning. Developed by researchers from UC …
-
LLMs generate enterprise workflows via compiled code for reliability
Two research papers explore methods for generating executable code from large language models to automate enterprise workflows, focusing on reliability and efficiency. The first paper details lessons learned from evalua…
-
DSPy's new RLM module tackles LLM context rot
The DSPy framework has introduced a new module, dspy.RLM, designed to address the issue of "context rot" in large language models. This phenomenon, identified by MIT researchers, describes how models lose performance on…
-
Prompt engineering boosts small language models for query routing
A new arXiv paper explores the effectiveness of prompt engineering techniques for small language models (SLMs) in performing guarded query routing. The study evaluated 22 SLMs on the GQR-Bench dataset, focusing on their…
-
Anthropic's Fable model excels at uncovering hidden task assumptions
The AI model Fable, from Anthropic, is being highlighted for its ability to uncover hidden decisions and assumptions within complex tasks. Unlike models that excel at executing predefined plans, Fable is particularly ad…
-
DSPy framework re-framed as a programming tool for LLMs
The DSPy framework is presented not merely as a tool for better prompt writing, but as a system for programming language models. Its core value lies in separating the task contract (inputs, outputs, measurable examples)…
-
DSPy framework enhances Datasette Agent's SQL prompt generation
Simon Willison explored using the DSPy framework to enhance the system prompts for Datasette Agent, a tool that generates SQL queries to answer data-related questions. He tasked Claude Code with evaluating and improving…
-
Prompt optimization may weaken LLM adversarial robustness, new benchmark suggests
A new benchmark has been developed to investigate whether prompt optimization techniques for Large Language Models (LLMs) weaken their robustness against adversarial attacks, specifically prompt injection. Initial findi…
-
New simulator automates air traffic controller training with adapted speech models
Researchers have developed ASTRA, a new simulator designed to train Air Traffic Control Operators (ATCOs) by automating the role of human simpilots. This system addresses the limitations of existing Western-centric spee…
-
Developer reviews 10 AI agent frameworks including LangGraph, CrewAI
This article provides a hands-on review of ten AI agent frameworks, focusing on their practical application for developers. The author tested tools like LangGraph, CrewAI, AutoGen, and OpenAI's Agents SDK, offering insi…
-
New research probes prompt optimization's effectiveness and interpretability
Two new research papers explore the effectiveness and interpretability of prompt optimization for large language models (LLMs). The first paper, iPOE, introduces a method that uses automatically generated guidelines fro…
-
New framework quantifies perturbation propagation in compound AI systems
Researchers have introduced QUIVER, a new formal framework designed to measure how perturbations propagate through compound AI systems that chain multiple large language model calls. This framework quantifies sensitivit…
-
AI app development demands specialized tech stacks over traditional ones
Developing AI applications requires a specialized tech stack that differs from traditional web development due to the non-deterministic nature of LLMs. Python and JavaScript/TypeScript are recommended for AI workflows a…
-
Neural1.5 method ranks second in clinical QA task
Researchers developed Neural1.5, a method for the ArchEHR-QA 2026 clinical question-answering task, which involves four subtasks: question interpretation, evidence identification, answer generation, and evidence alignme…
-
Nous Research launches Hermes AI agent for rapid data analysis
Nous Research has introduced Hermes, an evolutionary AI agent framework designed for rapid data gathering and analysis. Unlike DSPy, which requires extensive programming and fine-tuning for specific tasks, Hermes offers…
-
LLM output validation and efficiency strategies detailed
Several articles discuss robust methods for handling Large Language Model (LLM) outputs in production environments, emphasizing the need for structured validation beyond simple JSON formatting. Techniques like Pydantic …
-
Prompt engineering advances with automated optimization and structured techniques
Prompt engineering is evolving into a systematic discipline, moving beyond simple instructions to advanced techniques for optimizing LLM output. Tools like DSPy automate prompt structure and example selection, transform…
-
New study compares automated vs. expert prompt engineering for LLMs
A new research paper explores the effectiveness of automated prompt optimization compared to expert-crafted prompts for large language models. The study systematically compared hand-crafted prompts, base DSPy signatures…
-
Agent Capsules optimize LLM pipelines for efficiency and quality control
Researchers have developed "Agent Capsules," an adaptive runtime system designed to optimize multi-agent large language model (LLM) pipelines. This system addresses the trade-off between token savings from merging agent…