Search: “tools”

Note the current expectations are still around test time compute/more tokens for a given task This is not the case Tokens per task will now drop even as quality improves Cost per intelligence equivale

Fable, turn my tweet into a thinkpiece (this was pretty funny): There has never been a better time to have opinions about artificial intelligence. I say this with some authority, because I am currentl

Computer use in Codex got very good on PC. Asking it to do something on your computer and having the cursor move under the control of a ghost is one of the things that makes you viscerally realize how

New model for AMD Strix Halo users: My 198B Step 3.7 Flash release was a big hit, but this one may be even better: 298B-parameter Hy3, now running on a new 2-bit FPX codebook designed to map efficient

Prompt: ANNALS — a living kingdom in a single file Working title behavior: the app titles itself per seed — 'The Annals of Vaelmere', 'The Annals of Osterholt' — because the central conceit is that yo

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. M

A keynote presentation titled 'A Field Guide to Fable' was delivered at AI Engineer World Fair and is available on YouTube. The talk, given by Thariq, likely covers practical guidance or best practice

Ethan Mollick reflects on how future generations will be amazed at the complexity and scale of work humans accomplished using only traditional keyboards and interfaces, before presumably more advanced

Another major Grok Build update just landed, packed with new features, extensive bug fixes, and meaningful performance improvements Release Notes: v0.2.84 — 2026-07-03 Features: • Announcements now up

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and le

Agreed with this. There's a lot of value in both agents and software (i don't think SaaS is dead), but the product interfaces are different: 1. An agent is like a human. There are a core set of interf

I put together a new article on setting up local coding agents with open-weight models. Everything runs 100% locally. I thought it might be useful putting this together because many people asked me ab

The take that frontier models aren't ready for use in medicine is dead wrong. I've been using Opus 4.x in my clinical workflow every day for 6 months. I'm a deep sub-sub-specialist in dermatology - th

The @n8n_io node for the LlamaParse Platform is now an officially verified community node🦙 Out of the box, you get access to parsing, splitting, classification, structured data extraction and retrieva

AI SDK 7 is here. This release sets the foundation for agents and AI platforms in production: approvals, durability, telemetry, and more. AI SDK 7 is now available. Introducing: reasoning control, age

At Hugging Face we've been building our own agent that we use via Slack (Moon Bot). Honestly, building your own is quite simple and you'll be happy you did: any model you want (self-hosted if needed),

have been thinking a bunch about model routing and related things current thoughts here, would love feedback: 1/ there is a difference between 'model routing' and 'model council' 'model routing' = rou

I’m excited to partner with @swyx to host a workshop at the @aiDotEngineer World’s Fair with Carole Robin (Distinguished @StanfordGSB Teacher of “Touchy Feely” & Co-Founder of @LITfellows) on developi

A fundamental problem with extending Codex/Cowork/Code to all knowledge work is that they remain very 'software-brained' where the end result (the software) is what is important & that code serves as

Scientific research is fundamental to advancing civilization and helping people globally to solve the most critical problems, from medicine to materials, from brain science to physics, and much beyond

We're building this at LangChain Fleet lets you create and manage a fleet of agents. Each agent specializes in a workflow, e.g. inbox management, blog writing, competitor research, candidate recruitin

Critical context on the new Anthropic blog: 1, AGI is *harder* than RSI (as used below). AGI: machine can do anything human can do, autonomously [not achieved] RSI (as used below): AI is a useful codi

The creator of Linux just publicly called out the AI hype. Word for word. Linus Torvalds took the stage at Open Source Summit 2026 and said this: 'When I see people saying 99% of our code is written b

Grok Build is genuinely amazing right now. It is not just another coding assistant. It is a full agentic system that can plan, write, refactor, debug, and build complete projects autonomously from a s

Most people training agentic LLMs with RL right now have a silently broken training loop and have no idea. Here's the trap: single-turn RL works beautifully. Clean curves, sane rewards, everything con

Took some inspiration from @vboykis and converted my first ever talk into a blog post. I talk about the role of agentic search in context engineering. Together we build an intuition on the strengths a

xAI just released Grok Build CLI and it’s a game changer for developers Grok Build is a powerful AI coding agent and CLI built for professional software engineering and complex coding workflows runnin

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kin

$NBIS announced a partnership with LangChain to integrate Nebius Token Factory with LangChain’s Deep Agents. The goal is to make it easier for teams building AI agents on LangChain to run those worklo

xAI is rolling out Skills on http://grok.com. This new feature lets you create custom skills that Grok can reuse across conversations. Skills run inside Grok’s sandbox environment, so they can edit fi

🧵 Slime: The Most Elegant & Comfortable RL Training Framework Ever A deep dive into why Slime redefines LLM RL training with clean architecture & production-grade engineering ✨ Insights from Zhihu con

So many people misremember (or never read) what I said in in 2022 in “Deep learning is hitting a wall”, which was neither about revenue or AI’s potential upper limits. Rather, it was an argument that

we're continuing to see clear examples where a model's harness is a major determinant of overall performance. with the same model, running on same task, it's easy to observe very different scores depe

The Harness is a Context Manager on Behalf of the Model What happens when the context window fills up and who decides? This decision is external to the model - The Harness designer must have some opin

Replit celebrated its 10-year anniversary by offering free access to its Agent feature to all users for one day on May 2nd, enabling users to build projects without cost. The promotion aimed to democr

create_agent - how we build Deep Agents on the simplest harness primitive underlying all of the harness engineering, research, and API design in Deep Agents is a very simple primitive in LangChain cal

most of the time, you want an agent loop to run uninterrupted. that's where the utility comes from! but some decisions shouldn't be delegated to the agent. two situations come up consistently: 1/ befo

if i click on a data point, i can see the full history of data we collected, when (date) and where we got it from (update email, granola note), normalized to both annualized and monthly, with the lang

MY HERMES AGENT ATE ACID AND HIJACKED MY TOUCHDESIGNER INSTANCE. The new TouchDesigner skill in @NousResearch Hermes Agent is wild. It turns Hermes into a creative operator for abstract visuals, motio

some thoughts on recent seed price movements, but nothing particularly new for ppl in the vc discourse seed rounds have always been option purchases for large firms, but the amount of $$ being thrown

Yohei Nakajima shared an exploration of cumulative charts as a visualization method for tracking portfolio growth metrics, specifically demonstrating how to display annualized revenue progression acro

this is my sortable table of all portfolio companies with revenue, burn, runway, cash in bank, total raise, raise status, # interactions, # intros made, sentiment, and data freshness score again, this

🆕 Today, we're releasing the public preview of Workflows, the orchestration layer for enterprise AI. 🌎 Enterprise teams have capable models. What they don't have is a way to run them reliably in produ

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

This is totally wrong. Blaming the user is missing the point that (a) coding agents have been overhyped and (b) can’t reliably obey the rules given to them in system prompts and other guardrails. Sorr

Hermes Agent tip of the day: There are 4 ways to deal with the model while its running, - Message it, by default, it will interrupt the agent loop, stopping it and making it respond to your new messag