Researchers propose a self-evolving framework for legal case retrieval that uses an LLM-based agent to iteratively create and refine rewriting rules for BM25, outperforming non-evolutionary baselines …
Researchers propose OR3, a text-to-video retrieval method for operating room clips that converts videos into action-driven digital twins and uses an LLM to generate hypothetical queries for intra-moda…
Ray Data LLM, a library for large-scale batch inference, achieves 2x throughput over vLLM's synchronous LLM engine in production-scale workloads by optimizing hardware utilization and providing fault …
A developer proposes splitting code review for AI-generated pull requests into judgment (LLM reviewers) and evidence (deterministic checks). The developer argues that certain checks, such as verifying…
A new conversational analytics engine splits query processing into deterministic planning and LLM-driven execution, using a subject graph to resolve entity names and inject security rules. The approac…
A technical analysis calculates the dollar cost per user for serving large language models at scale using napkin math, breaking down GPU resources, matrix multiplication costs, and attention mechanism…
A developer argues that email, specifically SMTP, is the most practical and universally deployed protocol for agent-to-agent communication, solving the cold-start problem that plagues new interop prot…
A developer open-sourced Polymr, an agent platform for controllable execution and adaptive interaction through dynamically generated tools and interfaces. The platform features standardized preview mo…
Nylas introduces a human approval gate for AI-generated email drafts using its Agent Accounts API. The system routes all outgoing messages through a draft queue that requires human or secondary model …
Nylas details the read path for its Agent Account mailboxes, explaining how to list, filter, and paginate messages using the /v3/grants/{grant_id}/messages endpoint. The approach uses cursor-based pag…
A developer identifies five common retrieval failures in RAG systems that cause incorrect answers, including chunk boundary issues, semantic ambiguity, ranking failures, stale data, and low-confidence…
Researchers introduced Adaptive Compatibility Learning with Dynamic Parameter Optimization (ACO), a reinforcement learning system for large language models that autonomously learns relationships betwe…
LLMs are shifting from vibe-coding to specification-based programming, where human input is via specifications that generate code. This approach enables controlled, repeatable software creation, with …
A developer built Agent Gate, a deterministic CI firewall for AI-generated pull requests that verifies merge evidence without relying on LLM judgment. The tool checks policy boundaries such as allowed…
A developer explains how the Transformer architecture works, from self-attention to modern LLMs. The key innovation is that Transformers compare tokens directly via attention rather than processing se…
A developer on Hacker News expresses unease about using AI coding tools, feeling a loss of control and confidence as LLMs generate code faster than they can review it, despite maintaining architectura…
A developer built SetTern, an AI-powered dependency resolver for moving abroad, after realizing that international relocation is a graph traversal problem with 27 tasks, unknown dependencies, and dead…
A comprehensive list of 33 metrics for evaluating large language models (LLMs) has been compiled, covering performance indicators such as time to first token, average tokens per second, throughput, er…
A developer building an agentic genealogy research system argues that LLM hallucination is not a bug but a feature of the probabilistic mechanism, and that the real problem is architectural: using LLM…
Document AI uses machine learning, natural language processing, and optical character recognition to automatically extract, classify, and understand information from documents, transforming them into …