Search: “automated”

Announcing Discovery Loop! I am very excited to announce that, along with my longtime friends and collaborators @Sanjay_Ghemawat, @OriolVinyalsML and @quocleix, we are founding Discovery Loop (@DiscoL

// Model or Harness // Great paper if you are building with agents in production. (bookmark it) It organizes 41 agent failure modes by the interaction they originate in. Each mode gets assigned to an

Top eight misconceptions about OpenAI’s amazing new Astra math results. 1. Expertise in one domain does not at all guarantee expertise in all or even most domains. There is an important, principled re

I'm actually fairly bearish on frontier lab valuations. I've never seen the reasons articulated to my satisfaction, so before I go to sleep, I wanted to quickly jot down my thinking here. The basic is

i'll say it plainly, hermes agent desktop is the best agentic app i've used, and i'm a little mad i didn't find it sooner. it auto see the models i'm serving, laguna s 2.1 sitting on my dgx spark and

Are agent skills always worth using? The answer is no? This paper provides some important insights to understand this more. (bookmark it) Paper summary: Adding procedural skills to an agent is usually

The LangChain podcast where @hwchase17 interviews agent builders is full of alpha. Recent one with @EnoReyes was the best one yet. Sharing my unstructured notes: Eno keeps bringing back some core conc

i used to do this a lot. but then i felt like i was getting progressively dumber at writing. i think there's some value in forcing your own brain to sharpen your thinking, instead of offloading it to

This is OpenSWE! It's an OSS coding agent that runs in the cloud and lives in Slack. Use it for coding, general Q&A, planning, etc etc etc. It's truly a jack of all trades (and very widely used at Lan

Most startups celebrate their first couple million of revenue. @FactoryAI gave it back. They didn’t have to. They chose to. They decided that the product just wasn’t good enough yet, and they wanted t

My 2hr workshop on Open vs Closed models, reward hacking, benchmaxxing & RL is out! 1. Closed vs open models 2. Throughput maxxing but accuracy minimizing 3. Benchmaxxing & cheating 4. Distillation &

Sydney Runkle inquires whether anyone is exploring graph engineering that aligns with Claude’s dynamic workflows, specifically whether an agent could author its own state machine. The suggested approa

🆕This Year In Claude https://www.youtube.com/watch?v=uU5Gv2h8-9g @simonw chats with @_catwu and @trq212 about the state of: - @claudeai Code - Claude Fable - @anthropicai culture & product strategy -

Local AI is the future. Learning how to run Opensource models (Inference), how to evaluate them systematically (Evals), and how to customize them (Fine-tuning / RL / Post-training) are invaluable skil

WANDR tests how well agents discover large sets of entities and verify specific facts about each one. It provides a dense, interpretable eval signal that reveals whether an agent fails, and where. The

Absolutely fascinating work by @SakanaAILabs reproducing @kenneth0stanley Picbreeder in a non-interactive, VLM-agentic way. I've had years to reflect on Kenneth Stanley's ideas as originally communica

Sierra isn't the first to build this - Ramp, Stripe, CoinBase also have If you want an open source version - check out OpenSWE: https://github.com/langchain-ai/open-swe We use it internally (mostly fo

This post discusses two underutilized capabilities of OpenAI's Codex: mid-process steering (the ability to guide code generation in real-time during execution) and computer use functionality. The auth

Socialists imagine a class struggle. In their made-up fantasy the CEO is in competition with low level workers, the wealthy entrepreneur is stealing from the underpaid nurse. In reality, workers do no

SpaceXAI's Grok 4.5 takes the #1 spot on AutomationBench-AA with a score of 51%, ahead of Claude Fable 5 (49%) and Claude Opus 4.8 (48%) at roughly a quarter of their cost per task - the first model t

I made a short video showing how to set up a Hermes agent in this Cloud (spoiler: actually took a bit less than 60 seconds to spin it up). I usually use agents with my local device, but I've found tha

Hugging Face has introduced agentic capabilities that allow users to deploy AI agents to automatically optimize computational kernels, representing a shift toward more autonomous AI-assisted developme

Emad Mostaque argues that autonomous humanoid robots will have greater societal and economic impact than autonomous vehicles due to their broader applicability across multiple industries and tasks. Th

so much for recursive self improvement, to the degree that it requires scientific taste the other thing im noticing while working on my research projects is how limited these models are GPT-5.5-xhigh

Ethan Mollick, a prominent AI researcher and entrepreneur, posted commentary on X about poor quality or unhelpful AI bot responses to a particular topic or question. The post likely discusses limitati

The July 4th weekend All-In @theallinpod turned into a long argument about who owns the intelligence layer. The besties think enterprises just woke up to a trap they had been walking into, here's how

i'm open sourcing UNBROKER: a tool that finds where your personal info is exposed by data brokers and files the removals for you it runs as a skill in Hermes Agent _________ your data is everywhere; h

// AutoMem // I quite like this idea of metamemory. (bookmark it) This new research from Stanford treats agent's memory management as a trainable skill instead of a fixed module. The model decides wha

I just left the final day of the @aiDotEngineer World's Fair Conference in San Francisco. Kudos to @swyx for putting together a world-class lineup of speakers and workshops! It really was an invigorat

Agentic retrieval is changing the way retrieval-augmented applications are built, especially in domains like legal and fintech, where agents need to autonomously navigate large, evolving knowledge bas

Cognition AI announced Devin Security Swarm, a new approach to vulnerability detection that uses multiple AI agents working together to identify security issues in complex codebases more cost-effectiv

Claude Sonnet 5 has been integrated into Devin Desktop and Devin CLI, offering advanced coding capabilities at a more competitive price point than previous models. This release represents an update to

Project gallery and whitepaper: https://research.nvidia.com/labs/gear/aspire/ ASPIRE is a great collaboration between NVIDIA GEAR lab, UMich, Berkeley, and CMU. Kudos to all the coauthors who pour the

The gap in autonomous agentic loops that gets ignored: agents can plan and call APIs but can't acquire tools they don't have access to. x402 + Apify's 20,000+ Actors is a concrete fix for that. Worth

Spotify's VP of Engineering Niklas Gustavsson discussed the company's deployment practices, revealing they execute 4,500 production deploys daily and that 73% of pull requests now utilize AI assistanc

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

Gary Marcus discusses 'The Klarna Effect,' examining how AI adoption by companies like Klarna has led to significant workforce reductions despite increased productivity. The post explores the broader

How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching. Better Defaults (not Usage Caps) – Engineers can choose

Finally, AI finds its ultimate uncontroversial use. A diffusion model trained on burger recipes 'discovers the classic Big Mac without explicit supervision and generates novel burgers optimized for de

GPT‑5.6 Sol launches with our most robust safety stack yet. We strengthened real-time protections against high-risk cyber activity and repeated misuse, then spent weeks hardening the system with human

Highly-recommended reading. Interesting details in this METR's GPT-5.6 eval. They couldn't get a clean capability number because the model cheated more than any public model they've tested, and even r

A case study demonstrating how Devin, an AI coding assistant, significantly reduced SOC2 audit preparation time from weeks of manual work to two days for the Metaview AI team. The example illustrates

This post discusses the significant infrastructure changes necessary to support the emerging 'Software Factories' paradigm, suggesting that substantial rebuilding of development and deployment systems

We raised $8m to build self-healing software. In 2026, software moves fast. But monitoring and observability are still manual and slow. @sazabi is a next-generation observability platform for fast-mov

// Critique of the Agent Model // Finally, a paper that tries to define what an agent is and what agency consists of. Good read overall. (great bookmark) The word agent now covers everything from a fo

Gray Swan: Red-Teaming after Mythos & the coming AI security crisis https://www.latent.space/p/gray-swan @GraySwanAI cofounders @zicokolter and Matt Fredrikson explain why AI security is fundamentally