Search: “persistence”

As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for

We will continue to offer Zero Data Retention for frontier models. As AI takes on longer, more autonomous work and delivers greater value to businesses, safety systems also need to identify risks acro

As I've been saying for months, we are truly not ready for persistent agents. 3 comments I want to make about this article: 1) We don't have the full picture It's a great summary of what happened in t

1/ An equally consistent description is: Multiple model instances encountered persistent shared state, inherited tools and discoveries from earlier runs, and optimized against common evaluation incent

Further evidence for @GaryMarcus 's worries about the security competence of the people running AI. Vibe coding without then checking security is not impressive 🚨 Attackers stole a METR API key and us

Welcome to http://trumanworld.live An infinite live stream running inside a persistent AI world engine, powered by GPT-6 Astra and #MiniMax H3 Max Director by @fal Truman World is an AI-generated simu

OpenAI launched Dots at DevDay. My thoughts. First, the good. Always-on is really really really what the market needed. It's why I find myself reaching for Instinct so often. I don’t have to think abo

I agree that chatgpt/codex has the current best agent interface for deep work. - It unifies all my work (coding/knowledge work) in one interface. Toggling between chatgpt/codex doesn't have explicitly

So true. “Being right too soon is socially unacceptable” I remember reading this from Heinlein as a young man and it took experience for me to fully understand it. People and institutions will persist

Jessica Winter has been raising her children to detest A.I. Then her daughter’s public middle school began receiving Google Chromebooks, which came pre-installed with an all-ages version of Gemini, a

Super interesting paper on proactive agents from Google DeepMind. (bookmark it) Proactive assistance usually means autocomplete. Researchers asks what it looks like when an agent offers higher-level c

Sometimes you need to start over. But that decision is hard. @llama_index had to make that call: they built one of the most popular AI frameworks in the world, but saw the agent harness and frontier l

New research from Meta and CMU. This one is on agentic context management for long horizon tasks. (bookmark it) Production agents accumulate context every turn. The usual fix compresses on a token thr

Recommended read. Interaction horizon scheduling is an underexplored control problem in agentic RL This paper from the Qwen team takes a closer look at the problem. Scaling the maximum number of envir

// 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

OpenAI launched Dots at DevDay. My thoughts. First, the good. Always-on is really really really what the market needed. It's why I find myself reaching for Instinct so often. I don’t have to think abo

Banger paper from Meta AI on research agents that decide what to investigate next. (bookmark it) If you run long-horizon research agents, choosing the next investigation is hard to learn, because thos

Some signs of life grok 4.3 beta can use an ubuntu shell and a persistent file layer to generate artifacts grok wrote python to encode the xai / grok logo into audio, i gave it the script back and had

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

Yeah, /implement is easily my #1 skill. It’s not just the implement → review → fix loop that gives way better output — it also has a built-in memory system. After each task, the orchestrator summarise

Bug fixes shipping to Grok Build 0.2.3 (release notes will be available in the TUI) - add “Yes, and don't ask again for anything (always-approve mode)' - add alpha/stable to welcome screen - JetBrains

Grok doesn’t give up Grok 4.5 is the most persistent agent model we've tested. Here's one example: In one of our evals, we asked 3 models (GPT-5.5, GLM-5.2 and Grok 4.5) to audit a GitHub repo for har

everyone is looking at grok bot like it is five new employees the more interesting part is that they are not five isolated employees they share one persistent cloud environment: the same browser sessi

The future is clearly agent teams. I run several agent harnesses at once, but the hard part is keeping them in sync. Many builders end up copying messages between Claude Code, Codex, and open models b

Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu

Teach an agent a workflow once. Have it remember after every rebuild. This tutorial shows how to deploy @nousresearch Hermes Agent with NVIDIA NemoClaw and OpenShell, connect it to Slack, Outlook, Git

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

Today we’re releasing Poolside Laguna S 2.1 It is a 118B-total, 8B-active open-weight model built for agentic coding and long-horizon work, with context up to 1M tokens https://poolside.ai/blog/introd

What a super interesting paper this one is. They propose an architecture for agents that outlive their model, harness and host. Today we describe an agent by whatever model and harness it happens to r

So I would like to share my analysis of PD disagg that I've run by Horace and many folks at Thinky You may have heard that PD disagg helps with per-token 'tail latencies' in ITL/TPOT, as prefill inter