time you have to learn something new: 2016: a quarter 2023: a sprint 2026: the meeting is in an hour

Agentic loops are stubborn, which is why agents are effective. However, in hardened enterprise environments, things start to break. How do they break, and how can you steer the agent's pivoting behavior the right way? Some findings from our research, Fable/Mythos included! 👾

if you can't clearly say it back - "the issue is X, the fix is Y, because Z" - please don't merge it

agent found your bug? cool. say it back: “so the issue was X” if you can’t, you don’t get to merge it

hey @steipete quick OpenClaw question: are you running one agent across everything with separate knowledge bases, or one for work, another for personal, etc.?

good news: a bad architecture decision now costs a few hundred bucks, not months bad news: i've made three this week

coding used to be "all you need is a laptop." now it's "all you need is a laptop and a payment method"

yes ai writes more slop yes it's also way easier to sort the slop

people keep telling me i'm flip flopping for saying codex > claude when not long ago i was the claude guy yes things change that fast yes codex 5.5 is that much better started tagging bugs by which model wrote them and claude is leading by a mile

no matter how fast you type, you usually give more context when you speak than when you write. agents perform better with that extra context, which makes voice-to-text a super powerful tool.

how i review prs now: - ask the agent to explain it in 50 words - keep asking questions until i actually get it

Anyone else seeing wild @OpenAI Codex usage spikes? Mine 10x'd today. Local event logs suggest subagents inherit re-count the parent's token history on spawn - one worker billed 387M tokens in its first 3 seconds. Looks like a fork/replay accounting bug. @OpenAIDevs

Today we're launching Accomplish FREE - powered by our new hybrid model router. Since we launched @Accomplish_ai a few weeks ago, we've been blown away by what users are building with it. Hundreds of thousands of you downloaded the app and took it for a spin, but one thing kept coming up: not everyone wants to bring their own API key just to get started. So today we're fixing that with free, built-in models - made possible by a massive shift that's happened in just the past few weeks: the rise of fully hosted open-weight models - locally on your @Windows machine with @nvidia @NVIDIAGeForce, on your Mac with @Apple MLX, or on @Accomplish_ai cloud, for FREE. Our new hybrid routing algorithm dynamically routes between cloud models and models running locally on your machine - optimizing for local execution by automatically detecting your hardware capabilities and each sub-task's complexity: coding, visuals, simple classifications - every LLM call is routed to the best model. We also brought some of our favorite enterprise features to the free tier: scheduled task dispatch, Google Workspace integration (@googledrive Docs, Sheets, Slides) via the new Google Workspace CLI, native Slack MCP connectivity, and more. Accomplish FREE is available for macOS, Windows, and Linux. Download, send a task - and boom, it just works with ZERO configuration! Download link in bio / first comment >>

Our best version yet

Today we are launching @openwork_ai, an open-source (MIT-licensed) computer-use agent that’s fast, cheap, and more secure. @openwork_ai  is the result of a short two-day hackathon our team decided to hack, which brings together some of our favorite open source AI modules into one powerful agent, to allow you to: 1. Bring your own model/API key (any provider and model supported by @opencode is supported by Openwork) 2. ~4x faster than Claude for Chrome/Cowork, and much more token-efficient, powered by dev-browser by @sawyerhood (legend) 3. More secure - contrary to Claude for Chrom/Cowork, does not leverage the main browser instance where you are logged into all services already. You login only to the services you need. This significantly reduces the risk of data loss in case of prompt injections, to which computer-use agents are highly exposed. 4. Free and 100% open-source! You can download the DMG (macOS only for now) or fork the github repo via the link in bio (@openwork_ai). Let us know what you think (or better, send a pull request)!