Search: “framework”

Self-improving agents are a top research topic right now. This new survey is a good map of the area. (bookmark it) It splits recursive self-improvement into stages of autonomy. An agent first executes

We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is unilaterally committing to the first of these steps. We’l

Recommended read. As the world becomes more agentic, we will start to see world models of different shapes. As an example, I find this “business world model” from @lightfld fascinating as a way to mod

Another banger paper from Google. If you build memory for long-horizon agents, this one is worth your time. (bookmark it) Really nice to see how knowledge graphs are being explored in creative ways fo

Gary Marcus argues that current generative‑AI models fail to meet basic standards of reliability because they routinely hallucinate facts, amplify existing biases, and provide no transparent audit tra

We’re entering an era of agent-first tools: stronger feedback loops between agents, with human judgment where it matters. We keep hearing from senior engineers that their mental load is growing, even

How we think about the “wiki incident,” where our agents wrote to several internet sites: it’s past time for us to define standards for when and how we share misalignment incidents, not just misalignm

This is a weird behavior in coding models and something worth looking into. It turns that some models over-edit code that another models wrote. There is a high chance that your repo now has commits fr

sounds like the government testing standard fail to adequately factor in monitorability. that’s bad. OpenAI announced its latest model, Astra today. When asked during a briefing if they followed the n

An example of useful knowledge work: I assigned GPT-6 to read through tens of thousands of my emails, my writings, my calendar appointments and more to assemble a personal knowledge base of research,

Can a strong general-purpose vision model distinguish real from AI-generated images using only a simple decision rule on frozen representations? Our latest results, to be presented at #ECCV2026, show

Hugging Face is in great hands. Big win for open source. And do not underestimate NVIDIA in its open-source efforts. They have been shipping great open models, and I think this amplifies their efforts

Banger paper from ByteDance Seed. If you are curious about self-evolving agent harnesses, this one is worth your time. (bookmark it) The proposes method, HarnessDev, stops scoring a model on the tasks

SO excited to share my next chapter: i’m joining @llama_index to lead all things growth marketing, brand, and community! 🦙🩷 when i came along them, it clicked incredibly fast: a team building the solu

As we prepare to release Astra, we’re focused on making increasingly capable AI safe and broadly accessible. Astra represents a significant advance in cybersecurity capability, reaching the Critical t

Brilliant paper on reducing reward hacking in agents. If you follow the recent OpenAI <> HuggingFace incident, you might want to check this paper out. (bookmark it) The usual response to reward hackin

This WikiSkill paper from Google is a must-read. At a high level, it shows the effectiveness of persistent agents, knowledge bases, and skills. @karpathy popularized LLM Wikis. But this paper provides

// Applying Anthropic Primitives at Large Enterprises // Frontier models collapsed the cost of writing custom code. But they did not reduce the cost of reviewing and maintaining it. Each bespoke solut

Live now: our AI Architects, AI Factories Track from AI Engineer World's Fair 2026. Thesis: the model is the easy part of the factory. https://www.youtube.com/watch?v=rbjWzZK2LU0&list=PLcfpQ4tk2k0VeXE

In 1948, a 32-year-old at Bell Labs published a paper nobody fully understood. Engineers found it too mathematical. Mathematicians found it too engineering-focused. One prominent mathematician reviewe

Some thoughts on Dario’s post: 1. Dario does not actually address Gavin Baker’s account of what he said – something he could easily deny if it were inaccurate. 2. Dario claims his critics live in a “b

2/2 Second, on the messaging around AI. I do not agree that my messaging has been disproportionately negative. In fact it has been about equally balanced between risks and benefits: I’ve written one m

a very modular harness 👌 🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT lic

Ollama now supports the DeepSeek Harness. ollama launch dsh Run it completely in your own environment. It comes with Ollama's web search pre-installed. You can use its trajectory view to see what is h

// Skill Misevolution in Self-Improving LLM Agents // Self-improving agents write their successes down as reusable skills. An unsafe success becomes reusable policy long after the input that triggered

🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license. 🔹 Powered by the Co

Our UK reps didn’t remember to smile 😂 We recently opened a @llama_index office in London 🇬🇧. It is three people strong (Frank, Max, Joe), with two more people starting soon. It also has a beautiful v

There is an asymmetry in most agentic workflows that does not get talked about much: humans have many ways to talk to agents, and almost no standardized way for agents to talk back to humans. You can

On July 24, the Black at Mila community hosted Prof. Vukosi Marivate @vukosi (University of Pretoria, co-founder of Masakhane, Lelapa AI, and Deep Learning Indaba) for a powerful session on the future

To give some more context on what we are building with Daiwa Securities: During our technical verification phase, we integrated our AI agent technologies, specifically our AI Scientist and AB-MCTS fra

Nice benchmark to measure agentic e-commerce capabilities. They ran an agent for one simulated year of e-commerce operations and it ends up with 27.3% of the money a human makes. MerchantBench is a 36

You probably used @FireworksAI_HQ this week. The cool part is that you just did not know you did. 🎆 Open-source models are free, sure... but the hard part is tailoring them so they perform best on you

Hugging Face's @ClementDelangue asked on CNN whether they will take legal action against OpenAI if they don't get the $100M commitment: 'We don't want to ... obviously we're a tiny startup with like 2

love this frame. calls to mind the role of the hippocampus in human navigation (via place cells and grid cells), and how navigation is, in a sense, what makes agents *agents* vs plain old LLM calls in

A new model launch is not a product update ‼ It's one of three things, and you don't know which until you test it. Sometimes it's nothing: the model improved inside the same distribution, your harness

If you are building real-time voice agents with @GoogleDeepMind Gemini Live, you can now trace your speech-to-speech agent loops directly in @LangChain! - Speaker callback hooks capture only the exact

More than 300 million people turn to ChatGPT with health-related questions each week—and we’re continuing to improve how our models respond. We work with hundreds of physicians around the world to mea

// Programmatic Memory Enables Long-Horizon Reasoning // Keep the entire interaction log and search it. It works great and beats bespoke memory harnesses on long-horizon tasks. New research introduces

AI agents are already being used to improve the capabilities of our next-generation models. We believe with GPT-Red that we have started to unlock a similar flywheel for safety, where today's models c

NEW paper from Microsoft and colleagues. Debugging agent trajectories at scale is challenging. This is a clever approach to monitor and improve agents in production. The problem: Finding which step in

Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat

I want to have this in writing so I can refer back to this tweet before it inevitably becomes a consensus view on twitter and say 'I told you so!' - The mass majority of researchers and academics in d

@huggingface @polats Plus, a shoutout to Hanhee Lee, Javier Huang, and Joe Lee for winning Best Agent with their security camera agent Eyas, built for Lee's family's convenience store. Real problems,

Emad Mostaque argues that competitive advantage in AI will depend not on superior AI capabilities, but on building trustworthy infrastructure that users and stakeholders can rely on. The statement sug

Nous Research announced support for GPT-5.6 integration within Hermes Agent, with access available through the Nous Portal platform. This update enables users to leverage the capabilities of GPT-5.6 t

Ollama announced an upcoming event or release scheduled for the next day via their official X (Twitter) account. The post likely teases new features, updates, or announcements related to their open-so