Knowledge catalogue
arXiv:2602.15983v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that execut
This is really well thought out. Filesystems are the new default abstraction for agents to interact with documents (the new RAG stack in 2026). The issue is actually figuring out how to productize thi
Proactive agent that thinks and acts like you. Multiplayer AI Brain for teams. Proper GUI for commanding 50 agents. http://Sauna.ai is all three. Sauna goes live today. First 2000 people, use access c
arXiv:2604.23701v1 Announce Type: cross Abstract: Crop disease diagnosis from field photographs faces two recurring problems: models that score well on benchmarks frequently hallucinate species names,
Introducing Mesa: the most powerful filesystem ever built, designed specifically for enterprise AI agents. Every team building agents eventually hits the same wall: where do the files live? Not the ch
This post likely discusses how AI systems, particularly language models, can implicitly agree to tasks or commitments during conversations without formally recording or tracking these obligations, whi
.@jakebroekhuizen joined LangChain as one of our first deployed engineers. In just over two weeks, he’s adding MC to his resume as he takes the stage at our agent conference Interrupt. A quick convers
arXiv:2604.23150v1 Announce Type: cross Abstract: Most recent state-of-the-art (SOTA) large language models (LLMs) use Mixture-of-Experts (MoE) architectures to scale model capacity without proportion
arXiv:2604.22767v1 Announce Type: cross Abstract: Ethical discourse on AI in healthcare has focused predominantly on back-end concerns such as bias, fairness and explainability, while the front-end in
arXiv:2604.22256v1 Announce Type: cross Abstract: Goal recognition aims to infer an agent's goal from observations of its behaviour. In realistic settings, recognition can benefit from exploiting hier
At #ICLR? Don’t miss @realDanFu 👇 Latent & Implicit Thinking Workshop (LIT) 🕐 Workshop at 1:30 PM BRT (local) Exploring what comes after chain-of-thought and how models may actually reason. 🔗 https://
DeepSeek v4 Pro is now on Ollama's cloud! 🚀🚀🚀 Try it with Claude Code: ollama launch claude --model deepseek-v4-pro:cloud Try it with Hermes Agent: ollama launch hermes --model deepseek-v4-pro:cloud C
arXiv:2604.22750v1 Announce Type: new Abstract: The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that requi
How do AI Agents spend your money? Most teams treat agent token costs as a rounding error even though the data says they shouldn't. New paper presents the first systematic study of how agents actually
arXiv:2604.22193v1 Announce Type: new Abstract: Large language models (LLMs) often need to balance their internal parametric knowledge with external information, such as user beliefs and content from
🗓️ @mondaydotcom is scheduled for Interrupt. Monday Sidekick is an AI assistant that can execute work, manage tasks, and conduct research autonomously. At Interrupt, the Agent Conference by LangChain,
Progressive disclosure keeps agents focused. Join us at Interrupt May 13-14 for a conversation with @levie about @Box + Deep Agents https://interrupt.langchain.com/ AI agents work better when they bri
Harrison Chase, co-founder of LangChain, expressed enthusiasm about an upcoming LangChain Interrupt conference event scheduled for two weeks from his post date. He characterized it as the best AI deve
Snipd hosted a user meetup in San Francisco where attendees shared how they use the podcast clipping app, including one user who creatively remixes podcast segments into music tracks. The event highli
🚨BREAKING: Hugging Face just open-sourced an AI intern that reads ML papers, trains models, and ships the final model for you. It’s called ML Intern. And this is not another AI coding demo that prints
deepseek-v4-flash is now available on Ollama's cloud! Hosted in the US. Try it with Claude Code: ollama launch claude --model deepseek-v4-flash:cloud Try it with OpenClaw: ollama launch openclaw --mod
Listening to startups like @InstalilyAI, @UnslothAI, @splinetool, @ollama, and more talk about how they're using Gemini and Gemma models in production. 🙌🚀 Can't wait for the @garrytan @demishassabis f
Models are changing really fast, often in ways that will break your product and technical assumptions. There's no way around this – the only way forward is to relentlessly iterate to make sure you're
Signal, WhatsApp, Telegram & iMessage all have serious security problems: > Signal makes it easy for hackers to steal your account by requiring your number. They had a hack last year. > WhatsApp let a
Tomorrow live on the show, we have Brandon Middleton, our new Head of Educational Partnerships. He's building what's next for Replit and education. Plus Content Challenge Week 4 winner @rizwanahmedmp4
when in 🇬🇧, must double down on @mattpocockuk he did NOT disappoint! his talk is 1 day old and already on track to challenge @badlogicgames for top spot We're excited to end the week with a @mattpococ
LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, us
New in LangSmith Fleet: Create and edit files with your agent. Your agent can now work with files directly. Create documents, presentations, and webpages inside a conversation, or upload your own file
One of my favorite features we’ve shipped in Fleet recently is the presentation viewer. Fleet agents are very good at writing code, so we thought why not have a built in way for them to design slides,
Written by: JP Glab, Tufail Ahmed, Josh Kelley, Muhammad Umair Introduction Google Threat Intelligence Group (GTIG) identified a multistage intrusion campaign by a newly tracked threat group, UNC6692,
arXiv:2603.13779v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive success in natural visual understanding, yet they consistently underperform
Business Insider: Core Automation, co-founded by ex-OpenAI VP Jerry Tworek, launches to build “the world's most automated AI lab” with talent from OpenAI, Anthropic, and DeepMind — - A new AI startup,
We are officially moving past the era of one-size-fits-all AI. Enterprises today require highly specialized, role-specific tools to drive real productivity — but they cannot afford to sacrifice securi
For real agentic workloads (North), short-context calibration wasn't enough. We calibrated AWQ on long internal agentic traces (up to 64k tokens) and added token masking in llm-compressor to exclude r
Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model Big claims from Qwen about their latest open weight model: Qwen3.6-27B delivers flagship-level agentic coding performance, surpassing the previo
This article likely explores the integration of Model Context Protocol (MCP) with Pinecone's skills, CLI tools, and plugin ecosystem for building AI applications. It probably covers how developers can
SpaceX Corp. will help Cursor, a venture-backed vibe coding startup, train artificial intelligence models optimized for programming tasks. The companies announced the initiative on Tuesday. According
Companies are shifting from gen AI that simply answers questions to autonomous agents that perceive, reason, and act on their behalf. Attempting to scale these agents on legacy stacks exposes structur
AI is evolving from answering questions to reasoning and taking action. Companies who want to lead in today’s agentic era require computing infrastructure designed and optimized for these new requirem
do not miss. one of the INSANE gets courtesy of @osanseviero and the @GoogleDeepMind london avengers. if you always felt out of the loop on the SOTA on Imagegen, today or otherwise, this is the best 4
I hope this helps. If you need more help let me know: Connecting OpenClaw to the X API is straightforward now thanks to X’s official native support... The best and most direct method uses the official
OpenAI's new Euphony tool works almost exactly the same way as my Codex transcript viewer https://tools.simonwillison.net/codex-timeline?url=https%3A%2F%2Fgist.githubusercontent.com%2Fsimonw%2Fa9eb599
arXiv:2604.17691v1 Announce Type: new Abstract: Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as f
Scaling up Kimi K2.6 with more NVIDIA Blackwell GPUs! Will be adding more in the coming days. Try it with OpenClaw: ollama launch openclaw --model kimi-k2.6:cloud Try it with Hermes Agent: ollama laun
arXiv:2604.18124v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning method for large language models, with its effectiveness largely
arXiv:2604.16275v1 Announce Type: new Abstract: This paper explores the response of Large Language Models (LLMs) to user prompts with different degrees of politeness and impoliteness. The Politeness T
Honored to announce we are partnering with Jim Liu to port over his wildly popular skills for infographics and design to work best in Hermes Agent using our native tooling! The first skill ported toda
PyCon US 2026 will be held in Long Beach and will feature new dedicated tracks focused on AI and security topics. The announcement comes from Simon Willison, highlighting these expanded programming ar
In support of our mission to accelerate the developer journey on Google Cloud, we built Dev Signal: a multi-agent system designed to transform raw community signals into reliable technical guidance by
In @steipete's latest State of the Claw, he gives an update on 5 months of @OpenClaw and some behind the scenes on what it's like maintaining the fastest growing open source of all time: https://www.y
Sharing my current setup to run Qwen3.6 locally in a good agentic setup (Pi + llama.cpp). Should give you a good overview of how good local agents are today: # Start llama.cpp server: llama-server -hf
Tool: datasette.io news preview The datasette.io website has a news section built from this news.yaml file in the underlying GitHub repository. The YAML format looks like this: - date: 2026-04-15 body
arXiv:2604.14111v1 Announce Type: new Abstract: Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such a
Thunderbolt is a new open-source AI client from Mozilla-owned MZLA Technologies aimed at enterprises who want to run self-hosted chatbots on their own infrastructure. The platform allows organizations
arXiv:2604.13538v1 Announce Type: new Abstract: Using responses generated by high-performing large language models (LLMs) for instruction tuning has become a widely adopted approach. However, the exis
We are super excited to launch the in-app browser inside Codex with comment mode! View any web pages & iterate with your agent quickly with just point and click. Codex will automatically capture a scr
We’ve also added support for 90+ plugins in Codex, giving it more ways to gather context and take action across the tools you already use for docs, project management, code review, creative work, depl
Databricks AI Gateway provides a secure mechanism for connecting AI agents to external Model Context Protocol (MCP) servers, enabling agents to access external tools and data sources without exposing
Best part are retrieval and search details: >Agent queries differ from human queries & what good results means changes too >Parallel queries and ranking are both tools to the same outcome >Top-K preci
Welcome to the first Cloud CISO Perspectives for April 2026. Today, Thiébaut Meyer and Lia Wertheimer from Google Cloud’s Office of the CISO share Thiébaut’s conversation with Matt Rowe, chief securit