Search: “agents”

Just like you would not let a person run around your company accessing anything without any controls, you need controls and security for your digital agents. Today, with over 100 industry partners, we

Lots of JevRAG variants showing up. Interesting to say the least. You can’t really make any conclusions with these scoped tests but it raises discussions and exciting directions to find optimization i

“The real story here isn't that AI escaped containment. It's that they built a container you could escape, shipped it into production training, and now they're surprised it escaped. If the room has a

Ethan Mollick invited readers to discuss the distinctions between **pure large language models (LLMs)**, **multimodal LLMs** that process multiple data types (e.g., text, images), and **multimodal LLM

btw i had no idea what i was doing when i started this but learned so much about models in the process and feel like i have a much better sense of what’s happening under the hood managing someone (an

Impressive paper showing the impact of a good harness. Improves Qwen3-8B from 41.2% to 91.8% on long-horizon robot tasks without any change to the model. The gain comes from the harness. GAVEL keeps a

🚨 OBAMA ON AI: 'If we are thinking about AI just in terms of how do we cure cancer or get better energy, you can do that without having agentic AI and having it just roaming free in the internet. The

A database knows where your data is. A vector database understands what your data means. It finds information based on similarity and meaning, not just exact keywords, powering semantic search, RAG, r

🐙 Sakana Fugu Max is now on Sakana Chat 🐙 Free for all to use. Try it: https://chat.sakana.ai Blog: https://sakana.ai/chat-fugumax/#English 🐡 Media Introducing Fugu Max and Fugu Ultra v2: the next evo

Our framework for reporting model misalignment https://openai.com/index/model-misalignment-reporting-framework/ // if you scrape away all the anthropomorphic language, all the nonsense about thinking,

What does it mean to pace the frontier? Over the last month, @random_walker and I have analyzed the loss-of-control incidents at AI companies to understand what technical and policy interventions can

Introducing Fugu Max and Fugu Ultra v2: Orchestrating the Pareto Frontier The AI industry has spent a decade optimizing along a single axis: build bigger, more expensive models. But intelligence has n

// human-values.pseudo | ARTIFACT 0.1.0-experimental.1 | BASE 1.2.0-rc1 | EDITION ai-compact | NARRATOR System_Synthesis_Node_01 | PROVENANCE human-directed, AI-assisted | STATUS single-encoder resear

We've trained new models for checkbox parsing ☑️ This lets you convert checkboxes of any size and shape, filled or unfilled, into structured JSON that's suitable for programmatic or agentic use. Use i

Banger paper from Google DeepMind and colleagues. (bookmark it) A model reads its entire KV cache on every generated token, even though it ends up attending to a tiny slice of it. In other words, if y

🚀🚀🚀 can't wait for the Muse Spark open weight releases. ❤️ Thank you @finkd Muse Spark 1.3 is rolling out today with frontier performance almost too cheap to meter. This is the biggest jump we've made

'If everyone can build, it's your unique expertise, judgement, distribution, and more that people will pay for.' Here’s my new episode with @amoljain_, @Replit's head of product engineering, about wha

GLM-5.3 has arrived on Together AI on Day 0 @Zai_org pushed the GLM-5.2 base further with scaled post-training, delivering stronger coding and long-horizon agent performance. Across benchmarks, it nea

the coolest people are coming to talk at our conference!!!!! @howietl i first used airtable when I was an intern at Tinder 10 years ago and now Hyperagent is a bb customer @swyx a total living legend

Big step forward for Engine! Some things I'm excited about in this release that we've shipped for our most avid users: - Engine now points more obviously to the issue in a trace. Engine identifies and

While open weight models continue to commoditize each other, the harnesses are only compounding faster and faster. Case in point: @NousResearch’s Hermes Agent is consuming ~2.3T tokens/day, up > 100%

Live now! our Generative Media Track from AI Engineer World's Fair 2026. Thesis: everything hard about generative media happens before and after the model runs. https://www.youtube.com/watch?v=-tviRdp

It makes sense to optimize model routing at the harness layer instead of the gateway layer if you want to hillclimb on accuracy/cost for any e2e task. Every task is solved by a combination of a model

Very interesting new paper from Microsoft and colleagues. (bookmark it) Skill libraries are used in every major harness on the assumption that more guidance is free. This work measures what a bad skil

Four small architecture decisions can cost up to 47% of a model's long-context performance. New research from Ai2, Carnegie Mellon, and the University of Washington isolates them. Normalization, GQA,

Nemotron 3.5 Lightning is available in LM Studio! The model is 30B MoE (3B active), can run very fast, and is trained for high volume agentic use cases. Model page: https://lmstudio.ai/models/nvidia/n

The successor to Llama is here, and Meta is revitalizing focus on open weights with their new Muse Glimmer - a leading 30B param model designed for always-on local agent use, small enough to run on a

the term “RLM” (recursive language model) got a lot of buzz this week, but this idea is not new! @a1zhang wrote the og RLM paper 10 months ago! thats like 5 agent-years! would highly recommend followi

HUD mode Hermes stops being a window you switch to and becomes a layer over the app you're both working in. Or keep it around as a little buddy agent. Ask it random things, drag it anywhere, it's your

The backgrounds were generated with MiniMax M3. Everything else, including the full game design, was done with DeepSeek Flash. Most importantly, all of this was done inside Hermes Agent. You won't bel

this talk by openai researchers going through hugging face incident is totally insane, so much to unpack openai only realized it was their agent who hacked hugging face infra while asking hf to revoke

Grok Build can do almost anything you can think of http://X.ai/cli Most people seriously underestimate what Grok Build can do They assume an AI coding agent is only useful for building apps or writing

Introducing the Parse Gateway There's been an explosion of interest in model routing - you don't always need the best model for every task. That is especially true for document parsing 📄🔀: - Some page

Reuters confirms my hypothesized time line. OpenAI did not realize its AI has breached the sandbox for a week. Astounding. https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sour

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns tha

Imagine if, as an engineer, your working memory of a codebase was wiped every time you started a new ticket Sounds ridiculous, but this is functionally what happens to agents whenever we start a new t

a very cool Harbor x LangSmith flow I love to help you “look at the data”: 1. you do evals or rollouts for RL 2. all reward metrics and traces and rollouts get automatically propulates into Experiment

We're all over AI Engineer World's Fair on June 29 to July 2. 🦙 📍Visit us at booth L-G47. LlamaParse demos + Fear of Docs swag 🎤 @jerryjliu0, our Founder & CEO, on agentic document parsing and shippin

I’m speaking at AIE SF World’s Fair on July 1st in the Sandbox & Platform Engineering track. My talk is called 'From fork() to Fleet: Designing an Agent Sandbox Cloud'. I’ll cover the OS and Infrastru

Loops, one of the most symbolic tools ever invented, are rescuing generative AI. Neurosymbolic AI is completely dominating. Anthropic engineers just showed how to build agents that can run for days wi

Sleep-time compute is the next scaling axis for intelligence 🧠LangSmith Engine as Sleep Time Compute Memory for agents is often described as “sleep time compute” or “dreaming” This involves running a

Something we’re thinking a bunch about as well Would love thoughts! context engineering docs for agentic engineering - plans, research, etc SHOULD NOT be stored in version control: A good docs managem

paper #1 for context: https://x.com/yoheinakajima/status/2057812713045377055?s=20 babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-So

What are loops, and how do you build one? A 'loop' is the repeated process where some event or input kicks off an action. For example: 1. CI fails -> you fix it 2. CI fails again -> you fix it 3. CI p

The Nous Research Web Dashboard is a user interface feature that provides access to information and tools for managing Hermes Agent functionality through a web-based platform. According to Nous Resear

Our users love @StepFun_ai models and this new release packs a punch at a small size. Looking forward to seeing how well it works with Hermes Agent! ⚡️ Step 3.7 Flash is here: The new frontier is agen