Search: “retrieval”

Super happy that a bunch of people are finding marlin useful. Thank you for the inference support @ZeroGPU_AI @huggingface 🥰🤝 We’ve got hands on more compute now so we’ll also release a series of blog

We launched Context Hub as a way to manage skills, AGENTS.md files, and other context files an agent might need You can easily use it as a virtual filesystem in deepagents See this video for more info

// Your Agents are Aging Too // Huh!? They need 'sleep,' and now they are aging? Joke aside, great write-up on reliable agentic engineering. This new research introduces AgingBench, a longitudinal rel

// Language Models Need Sleep // Let your agents 'sleep', folks. On a serious note, this is a fascinating paper on getting the most from long-horizon agents. Here is the problem with agents today: Att

Jerry Liu announced digital advertisements at the SF Caltrain station during Memorial Day weekend, mentioning the parsing of PDFs and a reference to '50' (likely indicating 50 PDFs or a related metric

Cohere Command A+ is now available in Microsoft Foundry as a Managed Compute offer. Cohere’s latest open-source model is built for enterprise-grade agentic AI workloads, bringing together reasoning, m

Personally incredibly exciting at LangChain Labs to lead a focused, applied research effort into Continual Learning. A big prior is in treating the long horizon agent optimization problem as one that

Excited to share our new paper: RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably LLMs often fail on inputs well within their advertised context lengths. We show that these fa

okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSi

The pure LLM debate - which I had for many years, here and elsewhere - is indeed no longer relevant. Why? Because I won; nobody uses pure LLMs anymore. Nowadays all deployed objects are neurosymbolic,

Great paper discussing agentic search vs. vector search. // Is Grep All You Need? // Pay attention to this on, AI devs. (bookmark it) They find that grep-style text search, when wrapped in the right a

Grok, through a standard subscription, now offers multiple AI capabilities beyond text chat, including image generation, web search via X, and image-to-video conversion. This represents an expansion o

Agents + file sandboxes are all in the range in 2026 🤖🗃️ This is a nifty reference implementation by @itsclelia showing you how to run your agent over a collection of docs (PDFs, images, Office) with

Anthropic just shipped sleep into agents. When you sleep, your hippocampus replays the day's neural sequences to the cortex during 150-220 Hz bursts called sharp-wave ripples. The replay runs about 20

JP Morgan's investment research team just shared exactly how they built their multi-agent system 'Ask David', and it's the same architecture pattern showing up everywhere: - supervisor agent orchestra

// Contextual Agentic Memory is a Memo, not True Memory // Most agent memory today isn't memory. They are more like memos. A new paper argues that vector stores, RAG buffers, and scratchpads implement

Swyx compares xAI's Grok codex functionality favorably to Slack's native AI search feature, suggesting it provides superior search capabilities within Slack. The post implies that Grok's codex indexin

Building a document processing pipeline at scale is hard, and is one of the reasons that it's hard to DIY your own document OCR solution by relying on LLM APIs. Your orchestration pipeline needs to ha

Building scalable, distributed document processing pipelines isn’t easy. That’s why we teamed up with @render to build a system that: 📝 Leverages the LlamaParse platform to parse, classify, extract, a

// OCR-Memory // Well this is a unique approach to store memory for long-horizon agents. Most of the agent memory systems compress trajectories into text summaries and hope the model remembers what ma

AI21 Labs announced that their Chief Product Officer Or Dagan presented at the DeepLearning.AI conference, discussing how the company achieved state-of-the-art results on the Browsecomp-Plus benchmark

'AI should elevate your thinking, not replace it.' I don't disagree, but the issue is that current LLMs are not really trained to support that out of the box. I've solved this by building my own agent

Organizational design for agents is hard, benchmarking agents working in concert is hard. Together, this is the next critical frontier for making AI matter in economically valuable tasks, and we reall

DeepSeek V4 by @deepseek_ai just dropped! SGLang is ready on Day 0 with a full stack of optimizations from architectures to low-level kernels. We also deliver a verified RL training pipeline in Miles

Good agent memory paper. And great insights on the benefits of structured memory for long-horizon behavior in LLMs. Why it matters: It treats memory less like search and more like a system that will n

Tool Attention Is All You Need // Tool Attention Is All You Need // New research proposes a practical fix for the hidden 'MCP tax.' The work introduces a dynamic tool gating mechanism built on an Inte

@benswerd there are tradeoffs but we've spoken to folks doing both inside and outside and the split is pretty much 50:50 in our experience. I've found @hwchase17's list of tradeoffs the most accurate

The Never Ending Lore of Harness w/@Vtrivedy10⚡️ Viv brought some amazing perspective around harness design, evals, file systems, RL Envs and so much. 0:00:00 - INTRO 0:03:30 - PhD at Temple Universit

fun off-the-cuff harness + agent engineering sesh with @dexhorthy @vaibcode @GeoffreyHuntley - a lot of good harness/agent design we’re doing today is still good context engineering, remember tool cal

good point about another benefit of open memory @hwchase17 Memory being open isn't just about lock in, it's about auditability. If a bad memory gets injected, you need to be able to see it, revoke it,

We only have spotty information about this very important topic. It suggests AI can be good at diagnosis, but the real world doesn't always match the experiments. https://x.com/emollick/status/1980474

Key to note that AI scientists are not experts on labor. Some other economists active on X doing work on AI & labor: @alexolegimas, @danielrock, @joshgans & @robseamans (among many others) But worth n

LangChain Community Spotlight: LangAlpha 💼 A coding tool built for Wall Street professionals, bringing AI-powered development to financial workflows. Check it out: https://news.ycombinator.com/from?si

Ethan Mollick observes that AI has fundamentally changed the landscape of human expertise and effort, as AI-generated content now permeates many domains that were previously built exclusively through

Million of recipes. Fuzzy ingredient data. One afternoon to solve it. 🍳⚡ Will Templeton, CTO and co-founder at Allspice, explains why Pinecone is their fundamental building block: ❌ No weeks of cluste

🆕 The Full Story of Notion AI https://latent.space/p/notion We're so excited to chat with @simonlast and @sarahmsachs about Notion's 'Token Town' - the crack team of AI Engineers and Model Behavior En

Jerry Liu, co-founder of LlamaIndex, shared a post on X (formerly Twitter) expressing enthusiasm about a notable development, likely related to AI, large language models, or the LlamaIndex ecosystem.

Harness Engineering Derived from what Models can’t do alone: It feels like a good time to step back and reshare some basic mental models for why harnesses exist in the first place - working backwards

MiniMax M2.7 is a large language model now available for local deployment through LM Studio, notable for its strong performance in agentic tool calling tasks. The model requires a substantial minimum

this is a fundamental building block for `deepagents deploy` we're designing a memory layer built for multi-tenant systems, so memory can be scoped to a user, agent, or organization please dm me if th

Harrison Chase discusses the tradeoff between speed and focus when building a core product using a frontier model versus developing more customized solutions. Using a frontier model with a standard ha

Harness, Memory, Context Fragments, & the Bitter Lesson this is a work in progress mental dump on interesting intersections between how we use and design a harness, implications for memory being accum

Harrison Chase (LangChain CEO) shared or engaged with a post discussing the evolution of AI application servers, drawing a parallel between traditional app server architectures and emerging AI infrast

Model providers don’t lock you in with the API. They lock you in with your own data. Memory is the moat. If you don’t own your agent’s harness, you don’t own your agent’s memory. And switching means s

Harrison Chase, co-founder and CEO of LangChain, made a post on X affirming a point about where value lies in AI systems, specifically arguing that value is found 'in the harness' — referring to the s

Harrison Chase, the co-founder and CEO of LangChain, shared or endorsed a post on X (formerly Twitter) expressing strong confidence in a particular approach, tool, or method, stating it 'works very we