Search: “tools”

Harrison Chase, co-founder of LangChain, discusses why agent harnesses are becoming the dominant architectural pattern for building AI agents, likely referencing a thread by Howie Chase (@hwchase17).

LangChains create-agent is a super minimal agent sdk If you want a more batteries included - that’s deepagents Middleware lets you extend both of them and customize behavior in a more advanced way @hw

Most people building AI agents don't realize this until it's too late. Your agent's memory isn't a feature. It's your moat. 1. Closed harness = they own your memory 2. Switch models → lose all context

On software engineering: → 56.22% SWE-Pro, matching GPT-5.3-Codex → 55.6% VIBE-Pro — full-stack project delivery → SWE Multilingual: 76.5 For agentic work: → Multi-agent collaboration built into the m

Nous Research has developed a skill optimized for processing and analyzing AI research papers, designed to work within their Hermes agent framework. The skill can be adapted and repurposed for researc

(thinking traces are always summaries of the internal reasoning, since the actual internal chain of thought is a trade secret, but that doesn't mean they aren't useful when summarized, especially when

Harrison Chase, the creator of LangChain, shared an article discussing agent harness design and memory architecture for AI systems. The post highlights approaches to structuring how agents manage and

Couldn’t agree more! We’re moving towards Nuerosymbolic AI - there’s masses just haven’t realized it yet, in the sense of understanding what the literature proposed and why the latest developments are

Esse post do Gary Marcus explica algo bem importante: a potencialidade que é o que chamamos IA Neurosimbólica: a combinação do melhor de dois mundos! Claude Code is not AGI, but it is the single bigge

Gary Marcus 又放大招了！ 他直接把 Claude Code 源码泄露后的核心真相点破： ✅ Claude Code 是 LLM 时代以来最大进步 ✅ 但它根本不是纯 LLM，也不是纯深度学习 ✅ 核心文件 print.ts 足足 3167 行，塞满了 if-then 分支 + 确定性符号逻辑 Anthropic 在关键时刻还是靠经典符号 AI来保底，才让 Agent 真正可靠。 这波操

Harrison Chase, the creator of LangChain, shared a post on X (formerly Twitter) likely related to AI agent development, LangChain updates, or the broader landscape of large language model applications

Ethan Mollick shared a humorous AI-generated image that 'fixes' Goya's famous dark painting *Saturn Devouring His Son* by replacing the disturbing scene with Saturn happily eating a hot dog instead. T

if you've read software history everything in your bone tells you open models have to win we are just in a weird anthropic fanboy moment we're seeing that open source models are getting good at file o

Harrison Chase, co-founder of LangChain, shared enthusiasm for a blog post about agent harnesses, describing it as one of the clearest and most practical explanations of why they are a lasting paradig

Most illuminating graph I have seen for definition of harness. Memory and context are deeply coupled with harness. In my humble opinion, how they are injected and managed are one of most important pie

Open Everything 🤝 Own your intelligence 🤝 Builder Choice We’re in the v0.1 of deploying agentic intelligence across the economy. Agents are data generating beasts! Experiential Memory: Each piece of g

the fact that http://pi.dev agent is so good, with virtually no sophisticated harness whatsoever, is a testament to the fact token vendor (codex/claude) agents are overrated. highly. today's moat of c

I was unable to retrieve the content of that specific X (Twitter) post, as web search results did not surface the tweet or its content. X.com posts are generally not indexed in a way that makes the...

Yep ... @GaryMarcus has been right for 25 years; some AI Godfathers, not so much at all! #SaturdayAISurvey @AnthropicAI Claude Code is not AGI, but it is the single biggest advance in AI since the LLM

As agent systems scale, the control layer becomes the main source of complexity. What starts simple turns into coordination and composition problems. I built langchain-middleware-stack to better struc

Garry @Kasparov63 retired from competitive chess over twenty years ago, and most or all of his tournament games are presumably publicly available - and yet I bet he still could crush any LLM that didn

Grok 4.20 hitting 83% on non-hallucination. Values truth. Claude ~74%. Others sitting in the 60s… or way lower. Less guessing. More honesty when it doesn’t know. That’s a different kind of intelligenc

LangChain's Middleware abstraction, introduced by Harrison Chase (@hwchase17) in LangChain 1.0 Alpha, addresses context engineering in AI agents by providing clean `before_model`, `after_model`, an...

In a world where writing code to build websites and apps is trivial (thank you Lovable, Cursor, Claude,...), the real differentiation for you and your company (and what makes you successful) will be h

The referenced tweet (status ID 2042696610614849548) is not publicly accessible via search, and the X.com URL requires JavaScript/login to render. Based on the available context from related search...

I wasn't able to retrieve the content of that specific tweet or URL from the search results. X (Twitter) posts are generally not indexed in a way that allows direct retrieval of their content, and ...

An **Open Harness** is a unified architectural layer that sits between AI agents and model providers, abstracting away provider-specific APIs and patterns. Because every AI agent harness has its o...

Sub-agent Model Selection — Different Tasks, Different Models Your main agent runs Qwen3.6-Plus for quality. But not every subtask needs a flagship model. Now sub-agents can use a different model. Cre

TGIF! Here are some of our favorite updates from the past week: — Notebooks in @GeminiApp, an integration with @NotebookLM that enables you to retrieve context from your private notebooks or convert y

The reaction people are having to AIs that can find bugs in code is fascinating. Finally, we have the capacity to fix the crisis in computer security we’ve had for decades, and everyone is treating it

tldr > evals are the new training data. instead of updating weights, you're updating the agent harness > problem is agents are famous cheaters. they will reward-hack your evals and overfit just to mak

Ultraplan, a planning feature in Claude, consumes approximately the same number of tokens and counts against subscription rate limits similarly to standard plan mode. Users should be aware that using

we are doing this podcast specifically to highlight the innermost details of building agents in production may be a little niche, but its a niche i like 🤷‍♂️ @hwchase17 Great content, really appreciat

Wrapped up the 3-day AI Engineer conference in London. Key takeaways: Planning & verification > implementation. Humans define what to build and validate it works. AI handles the coding. The harness ma

A bit over a decade ago, we got fuzzers. A fuzzer is an automated vulnerability-finder that repeatedly runs a target program with semi-random inputs. One particular fuzzer, American Fuzzy Lop, was not

After playing with it a bit, Meta's Muse Spark Thinking is fine so far, but really doesn't match the current Big Three models. It also is a bit... weird. Like some strange language & tone, a little lo

Can’t get enough of Harrison and his AI takes? Lucky for you, we’re announcing Max Agency where you can hear him & other industry experts talk agents, harnesses, models, evals, and more!! 🎙️Introducin

The referenced tweet (from @himanshustwts) is not publicly accessible without a login, so its exact content cannot be retrieved. However, based on contextual search results, this post appears to be...

Rob Schaper posted a reply on X (Twitter) praising Harrison Chase (@hwchase17) and the LangChain team for their work on agent harnesses, predicting the concept would become widespread within days. ...

I was unable to retrieve the specific X (Twitter) post at the URL provided, as the content is not accessible through search results. The tweet's text snippet ('memory is context, and context is wha...

I know it's self serving to say, but man I would've killed for a resource like Tinker and the tutorials, the cookbook, etc back when I was in undergrad. Following @karpathy blogs and training RNNs on

The specific tweet (status ID 2042224314494161089) was not directly retrievable from search results, but the broader context of the 'Is OpenAI trying to become Anthropic, while Anthropic becomes Op...

Our company mission today is to give AI agents the highest-quality document context. The native open-source libs that agents have access to (e.g. PyPDF) do naive text extraction. But this is incomplet

The specific post at URL `https://x.com/sydneyrunkle/status/2042269358756397525` was not found in the search results, and the post ID does not match any retrieved content. The closest post found (s...

Routing every task to your largest model burns tokens, adds latency, and inflates costs. @AI21Labs' Maestro Orchestration Meta Model (OMM) is the layer above your stack that dynamically selects the ri

// Scaling Coding Agents via Atomic Skills // Most coding agents train end-to-end on full tasks like resolving GitHub issues. But complex software engineering is really a composition of simpler skills