Tag
The author reflects on four papers from CHI 2026, particularly one examining how AI writing tools with LLM-based suggestions can reduce gender bias in hiring evaluations, discussing ethical implications and personal inspiration.
The article argues that AI labs should start funding historical research, showcasing how frontier LLMs like GPT-6 can tackle historical problems such as cryptography and text tracing, potentially leading to significant advances in historical knowledge.
A tweet highlights that venture capitalists are using LLMs to analyze pitches, advising founders to tailor their communication to influence these AI models.
The article explores the key challenges in transitioning LLM application ideas to production in the EU, covering legal compliance, traceability, abuse prevention, and accountability, and seeks concrete examples from practitioners.
OpenAI is expanding its AI agent capabilities to automate tasks for various professions with the launch of ChatGPT Work, aiming to make AI accessible beyond software engineers while raising concerns about data control and adoption.
The article explains the key differences between DevOps, MLOps, and LLMOps, highlighting how each addresses distinct challenges in software development, machine learning, and LLM applications, with a focus on unique monitoring and optimization in LLMOps.
The project lets users prompt AI agents to play 1v1 football in a physics-based simulation, evaluating how well prompts translate to actions in embodied environments.
SemaPLC is a verification-gated agent harness for PLC code generation that uses external compilation and live runtime execution to achieve higher verified pass rates than baseline methods.
This study investigates how class imbalance and batch processing affect LLM-based screening in systematic reviews, revealing that batch processing significantly alters decision-making behavior while prevalence metadata has minimal impact.
Fence proposes using Small Language Models trained on high-quality synthetic data as specialized guardrails for LLM applications, demonstrating performance gains over prompt-based LLM guardrails.
A perspective on how task complexity (measured in bits to specify a task) creates opportunities for AI startups to build software scaffolding around frontier models, especially for high-complexity and hard-to-verify tasks.
Manning Books announces a new early access book 'Building LLM Applications with DSPy', teaching how to use the DSPy framework to optimize LLM prompts with Python. The book is 50% off through June 3rd.
This tweet promotes a library that enables full observability and automatic analytics for LLM-based applications with just one line of code, claiming it provides valuable information for free.
A team is winning local trivia nights using an AI model with continuous time awareness.
Tim Davis, head of Modular, shares his experience building an autonomous code-writing system called Compound Loop and argues that software development is shifting from deterministic to probabilistic systems, with AI agents enabling a '24-7 employee' model where human operators coordinate rather than type, while roles are splitting between high-leverage positions and lower-value agent-wrangling work.