Ben Miller

🇪🇺🇦🇹 Tech-Enthusiast. AI Tinkerer. Into @OpenClaw. Former Tech Editor. Prev Apple PR; Burson - Qualcomm, Google, Accenture. Supporter of 🇺🇦.

[Ben Miller @bensen]

@sephmartinmusic It shows you how to access it through the backdoor

[Ben Miller @bensen]

Everyone's always talking about agents for coders, agents for sellers, agents for investors, agents for marketers, but no one ever talks about agents for proctologists
https://t.co/oi4FCczptm

[OpenClaw🦞 @openclaw]

Agents should learn repeated work, but not by silently rewriting future runs.

Skill Workshop turns reusable agent lessons into reviewable proposals you can tweak, apply, or reject before they become live skills. https://t.co/g6TfHBi5NC

[Ben Miller @bensen]

"Skill Workshop is OpenClaw's governed path for creating and updating workspace skills."

[OpenClaw🦞 @openclaw]

OpenClaw 2026.6.1 is live 🦞

🪟 native Windows node host
🛠️ Skill Workshop for self-learning agents
📋 Workboard orchestration
🧠 MiniMax M3 support

Windows joins the cluster. No penguin costume required.
https://t.co/xgCOdENFgQ

[Peter Steinberger 🦞 @steipete]

We never had more npm downloads than this week on @openclaw - comined with Docker, GitHub, company-internal deployments and the numerous forks, real number is more in the 10-20 million downloads/week.

[Ben Miller @bensen]

In the last 98 days since February 25, over 650 contributers have shaped and helped ship 144 OpenClaw releases, including 50 stable releases, with over 200 documented security-relevant improvements and hardening items across sandboxing, auth, exec approvals, SSRF protection, channel authorization, secrets handling, plugins, and audit coverage.

That’s a lot of fundamental updates and improvements to security in less than 100 days, many of which were developed in collaboration with companies such as Microsoft and Nvidia, hence why opinions can and have changed and comments made 100 days ago are long outdated.

If you want to bring yourself up-to-date, you can read more about that here: https://t.co/uCcEQn9POn

[9to5Mac @9to5mac]

Here's a look inside Apple's first developer center in Europe https://t.co/LjrDRWZ0pn by @benlovejoy

[Justin Ryan ᯅ @justinryanio]

Apple just announced its first European Apple Developer Center, opening in Berlin later this year.

The center will offer training, workshops, and support for developers building apps across Apple’s platforms, including Apple Vision Pro.

[Jennifer Marsman @jennifermarsman]

Using Microsoft Execution Containers (https://t.co/2growXMNL3), you can run OpenClaw natively on Windows, and the sandbox prevented deletion of all files on the Desktop. Running OpenClaw more safely in an enterprise is "pretty dope". :) https://t.co/wW2Y3dUm9r

[stevibe @stevibe]

Qwen3.6 35B A3B can't fill out a paper form on its own. But give it NVIDIA's LocateAnything-3B — the #1 trending model on HuggingFace — as its eyes, and the two small models get it done together.

(The test: place each element at the right pixel position on a blank form image, not type into a field.)

Setup:
> Qwen is the brain (main model), LocateAnything is the eyes (helper model acting as a tool).
> I gave Qwen a new tool: ask "where's the email field?" and LocateAnything returns the exact x, y, width, height.
> The blue boxes on the screen are its detections. Look how tight they are — it nails every field.

Result:
> Qwen3.6 35B A3B + LocateAnything-3B: form completed, all info correct.
> Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code: all landed in the right field areas.
> Character-box alignment still a touch loose, but every value is where it belongs.
> 9m10s, 224.5k input, 24.3k output, 21 turns.

Why it matters:
> Qwen alone can't finish this test. Bolt on a 3B model that does exactly one thing > locate > and suddenly it can.
> A combination of small models can do the work of a single large one.

[Ben Miller @bensen]

@davemorin @christofsalis @steipete @vincent_koc @satyanadella @Microsoft @Windows @Azure @openclaw

[Omar Shahine @OmarShahine]

Introducing Microsoft Scout, the first autopilot agent from Microsoft - 57 days after starting my new job, we are launching Microsoft Scout to our Frontier customers. Big day for the team and for @openclaw #MicrosoftBuild https://t.co/ZGl47ADnCg

[Vincent Koc @vincent_koc]

Thanks @shanselman and Samantha Song for a live demo of OpenClaw on Windows at Microsoft Build. You are braver than me!

[OpenClaw🦞 @openclaw]

"You can run OpenClaw inside your company now." Annoucing our work with @Microsoft to bring OpenClaw to the Microsoft and Windows ecosystems. Claws now work securly in the enterprise.

[Ben Miller @bensen]

Blog: https://t.co/qJdWv7WTTX

[Ben Miller @bensen]

OpenClaw runs natively on Windows leveraging MXC
"The Windows node and gateway run contained, so your system stays secure. You can easily install and use @OpenClaw in @Windows with its own companion app and set up your own claws or connect to existing ones, available in open-source. We are invested in continuing to make #OpenClaw run securely on Windows." #MSBuild

[Peter Steinberger 🦞 @steipete]

I told codex to use https://t.co/oHS8ombQcW whenever I'm distracted and it needs my help to be unblocked, and ever once it a while I hear it talking to me, and it's the coolest thing ever. (e.g. for releases, that needs npm and is 1Password-gated)

[Armin Ronacher ⇌ @mitsuhiko]

Heads up: we're hiring members of the technical staff at Earendil again. If you're interested mail [email protected]

[jay @mewtyunjay]

Little-known Codex trick: you don’t need the full Codex app running on a remote server for Codex on phone. Just run:

codex remote-control

and the machine shows up in your Codex mobile app as a controllable remote environment.

[Ben Miller @bensen]

@steipete @HopeForTheWorl1 https://t.co/nasnAMjXLz

[Justin Schroeder @jpschroeder]

Announcing: API for Cursor – use Composer 2.5 with any harness.

An open source macOS app that exposes an API for Cursor's models. Instantly use Composer 2.5 in Codex, OpenCode, Cline etc...

➡️ https://t.co/SeoJtR5T2l