News

How Personas Can Influence Agents to Play Split or Steal

Personas are often employed to guide large language model agents, yet their effectiveness in shaping strategic behavior in social dilemma settings remains uncertain. To address this, we examined the impact of persona pro

Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving

Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models,

Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarks

LLM conformity is often used to describe cases where a model changes a correct answer toward a peer or group response. We show that most of this apparent conformity survives even after the peer is removed. The reason is

The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgment

Large language models (LLMs) increasingly issue judgments read as binary verdicts, and a growing literature reports such judgments shifting under logically irrelevant changes of wording - among them an amplified yes-no b

Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation

Survey-style evaluations of large language models often treat a prompted response as a measure of a model's values or beliefs. This assumption is particularly fragile when responses are read as evidence of political valu

Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG

Multimodal retrieval-augmented generation (RAG) grounds a generator in evidence drawn from heterogeneous modalities -- text, tables, and images. The dominant deployment choice is binary and made before the model has trie

PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models

Integrating external tools with Large Language Models (LLMs) has emerged as a promising paradigm for accomplishing complex tasks. Since LLMs still struggle to effectively manage large tool collections, researchers have b

Prompting Beats Fine-Tuning: Generative Expected Value Scoring for Statutory Term Retrieval

Legal concepts in statutes are often expressed using vague terms, and practitioners frequently turn to case law to interpret them. We study the task of ranking case-law sentences by their usefulness for explaining a conc

Retrieving a Set, Not Independent Passages: Set-Level Compatibility Learning for Efficient Set Exploration

Multi-hop question answering and retrieval-augmented reasoning require selecting evidence passages that are jointly useful for answering a query. However, most retrievers still score passages independently or make locall

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models

Late-interaction retrieval models that use the MaxSim similarity function have shown strong empirical performance, often outperforming single-vector dense and sparse retrieval models. Despite these empirical findings, li

github-code Web Component

Tool: github-code Web Component An experimental Web Component built using GPT-5.5 and the following prompt : let's build a Web Component for embedding code from GitHub <github-code href="https://github.com/simonw/sqli

Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot

llm-coding-agent 0.1a0

Release: llm-coding-agent 0.1a0 Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it. I started a new Pyt

Structured memory filtering with metadata in AgentCore Memory

In this post, you will learn how metadata works across configuration, ingestion, and retrieval, explore enterprise use cases including multi-agent and multi-tenant architectures, and discover best practices for implement

Show HN: fenic – LLMs as dataframe operators, query meaning and structure

Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding

Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding This is an interesting new open weights (MIT licensed) model, the first model release from DeepReinforce. [...] with variants including 9B Dense, 31B Dense, 35B MoE, a

Using Local Coding Agents

Using Open-Weight Models in Local Coding Harnesses as an Alternative to Claude Code and Codex Subscriptions

Show HN: RAG Vector DB Cost Calculator

Run a vLLM Server on HF Jobs in One Command

Show HN: Sipp – Run small local LLMs in browser 3x faster

OpenAI and Broadcom unveil LLM-optimized inference chip

OpenAI and Broadcom introduce Jalapeño, a custom AI chip built for LLM inference to improve performance, efficiency, and scale across AI systems.

Experimenting with the proposed Cross-Origin Storage API in Transformers.js

Quantifying LLM Cost Savings from Cache-Aware Inference Routing

Our new community investments in Virginia support local jobs and expand energy affordability.

We’re helping build the state’s next-generation workforce and investing in energy programs.

LLM Research Papers: The 2026 List (January to May)

A curated roundup of notable LLM research papers that came out this year

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

How Virgin Atlantic ships faster with Codex

How Virgin Atlantic used Codex to ship its revamped mobile app on a fixed holiday travel deadline, reaching near-total unit test coverage and zero P1 defects.

Build a Coding Assistant with Weaviate MCP: RAG over Code & Docs

Use Weaviate's built-in MCP server to give Claude Code, Cursor, and VS Code hybrid search over your codebase and docs. No glue code.

We’re announcing new community investments in Missouri.

We’re helping build the state’s next-generation workforce and investing in energy programs.

Google just redesigned the search box for the first time in 25 years — here’s why it matters more than you think.

For a quarter century, the Google search box has been one of the most recognizable interfaces in computing: a thin white rectangle, a blinking cursor, a few typed words, and a list of blue links. On Tuesday, Google will

How GoPerfect Built an Agentic Recruiting Workforce with Qdrant Cloud

GoPerfect mission is to use an AI recruiting workforce that replaces the manual, low-leverage parts of recruiting. Instead, an agent decomposes recruiter intent and runs the work end to end to find top talent. Their agen

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context Costs

Strengthening Singapore’s AI Future: A New National Partnership

Google DeepMind and Singapore partner to apply frontier AI to address complex challenges across health, education, and sustainability and more.

Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality

Parloa builds service agents customers want to talk to

Parloa leverages OpenAI models to power scalable, voice-driven AI customer service agents, enabling enterprises to design, simulate, and deploy reliable, real-time interactions.

Your LLM Is Only as Good as What It Retrieves

A Researcher's Perspective on Retrieval Quality in RAG Systems

How Data Graphs Built a True Hybrid Graph RAG Platform

Data Graphs is a UK-based platform company that provides a knowledge graph-as-a-service polystore, built on a proprietary, high-performance graph database engine. Co-founded by Paul Wilton over 10 years ago as a consulta

My Workflow for Understanding LLM Architectures

A learning-oriented workflow for understanding new open-weight model releases

AI fundamentals

Learn what AI is, how it works, and how tools like ChatGPT use large language models. A clear, beginner-friendly guide to understanding artificial intelligence.

CyberAgent moves faster with ChatGPT Enterprise and Codex

CyberAgent uses ChatGPT Enterprise and Codex to securely scale AI adoption, improve quality, and accelerate decisions across advertising, media, and gaming.

Components of A Coding Agent

How coding agents use tools, memory, and repo context to make LLMs work better in practice

Multimodal Embeddings and RAG: A Practical Guide

Multimodal embeddings allow AI systems to search and reason across text, images, audio, and video in their native formats. This blog covers the key intuitions behind how this all works and walks through three practical i

Your Code is Your Schema: Weaviate Managed C# Client

Use semantic search and RAG in C# with the Weaviate Managed .NET client — attribute-driven schema, type-safe queries, and safe migrations, all in idiomatic .NET.

Qdrant Skills for AI Agents

The standard RAG tutorial teaches a simple pattern: embed your documents, store them in a vector database, retrieve the top K, and feed them to the LLM. The vector engine is passive infrastructure. Put vectors in, get ne

Master Multi-Vector Search With Qdrant

Most vector search tutorials stop at single-vector embeddings: one document, one vector, one similarity score. That works for demos. It falls apart when your retrieval pipeline needs to capture fine-grained token-level i

We Raised $50M to Build Composable Vector Search as Core Infrastructure

Today we’re announcing $50 million in Series B funding, led by AVP, with participation from Bosch Ventures, Unusual Ventures, Spark Capital, and 42CAP. Retrieval Is on the Critical Path of Every AI System Every ser

Building A Legal RAG App in 36 Hours

Learn how we built a production-ready, end-to-end RAG application in just 36 hours using the Query Agent and the new Weaviate Agent Skills library.

After Orthogonality: Virtue-Ethical Agency and AI Alignment

Preface This essay argues that rational people don’t have goals, and that rational AIs shouldn’t have goals. Human actions are rational not because we direct them at some final ‘goals,’ but be

Railway secures $100 million to challenge AWS with AI-native cloud infrastructure

Railway , a San Francisco-based cloud platform that has quietly amassed two million developers without spending a dollar on marketing, announced Thursday that it raised $100 million in a Series B funding round, as surgin

Claude Code costs up to $200 a month. Goose does the same thing for free.

The artificial intelligence coding revolution comes with a catch: it's expensive. Claude Code , Anthropic's terminal-based AI agent that can write, debug, and deploy code autonomously, has captured the imaginat

Listen Labs raises $69M after viral billboard hiring stunt to scale AI customer interviews

Alfred Wahlforss was running out of options. His startup, Listen Labs , needed to hire over 100 engineers, but competing against Mark Zuckerberg's $100 million offers seemed impossible. So he spent $5,000 — a fifth

Salesforce rolls out new Slackbot AI agent as it battles Microsoft and Google in workplace AI

Salesforce on Tuesday launched an entirely rebuilt version of Slackbot , the company's workplace assistant, transforming it from a simple notification tool into what executives describe as a fully powered AI agent c

FACTS Benchmark Suite: Systematically evaluating the factuality of large language models

Systematically evaluating the factuality of large language models with the FACTS Benchmark Suite.

Google DeepMind supports U.S. Department of Energy on Genesis: a national mission to accelerate innovation and scientific discovery

Google DeepMind and the DOE partner on Genesis, a new effort to accelerate science with AI.

How AI is giving Northern Ireland teachers time back

A six-month long pilot program with the Northern Ireland Education Authority’s C2k initiative found that integrating Gemini and other generative AI tools saved participating teachers an average of 10 hours per week.

T5Gemma: A new collection of encoder-decoder Gemma models

Introducing T5Gemma, a new collection of encoder-decoder LLMs.

AGI Is Not Multimodal

"In projecting language back as the model for thought, we lose sight of the tacit embodied understanding that undergirds our intelligence." –Terry Winograd The recent successes of generative AI models have convinc

Shape, Symmetries, and Structure: The Changing Role of Mathematics in Machine Learning Research

What is the Role of Mathematics in Modern Machine Learning? The past decade has witnessed a shift in how progress is made in machine learning. Research involving carefully designed and mathematically principled architect

What's Missing From LLM Chatbots: A Sense of Purpose

LLM-based chatbots’ capabilities have been advancing every month. These improvements are mostly measured by benchmarks like MMLU, HumanEval, and MATH (e.g. sonnet 3.5, gpt-4o). However, as these measures get more

We Need Positive Visions for AI Grounded in Wellbeing

Introduction Imagine yourself a decade ago, jumping directly into the present shock of conversing naturally with an encyclopedic AI that crafts images, writes code, and debates philosophy. Won’t this technology al