imtruebydesign

[imtruebydesign @imtruebydesign]

Hey chat beanz and cheese please activate @Muse in the UK. @ChatGPT

[imtruebydesign @imtruebydesign]

@techartist_ Looks amazing. Well done.

[imtruebydesign @imtruebydesign]

@thegreatest_sv It’s great, can you share the workflow to get it.

[imtruebydesign @imtruebydesign]

Lego headz

[kiosa @thegreatest_sv]

holy f*ck, you WILL lose your job in 2027 if you don't learn this.

not to AI. to the person next to you who runs 5 agents while you're still clicking through 1 app.

one person with the right agent stack now does modeling, materials, design, video and research before your first meeting ends.

10 repos to learn before it's too late:

1. dream-loop - YOUR AI 3D ART DIRECTOR

the agent imagines the final scene, builds it in Blender, and a critic agent checks it until it matches.

https://t.co/10UTzrCRWu

2. Blender Skills - PRO BLENDER WORKFLOWS FOR YOUR AGENT

modeling, UVs and more as ready skills for Claude Code, Codex and Cursor.

https://t.co/hTtW55HD5L

3. TRELLIS.2 - ONE IMAGE IN, ONE 3D ASSET OUT

detailed shapes with realistic PBR materials, by Microsoft.

https://t.co/PK32fkHov9

4. Open Design - AN AI DESIGN STUDIO ON YOUR LAPTOP

motion, prototypes, websites and apps with an agent. local-first and open source.

https://t.co/vhYfJ8QAHj

5. Impeccable - GIVE YOUR AGENT DESIGN TASTE

critique, audit, polish and catch the AI slop before your client does.

https://t.co/n1NRFu0sgs

6. HyperFrames - WRITE HTML, GET A VIDEO

built for agents. your promo is now a file, not a week of editing.

https://t.co/TyUf1vGcBb

7. Superpowers - MAKE YOUR AGENT WORK LIKE A SENIOR

it plans before it builds, tests its own work and debugs instead of guessing.

https://t.co/1QGlFnjon4

8. Graphify - YOUR COMPANY'S MEMORY

turns code, docs, SQL and PDFs into a knowledge graph your agent can actually query.

https://t.co/4jokm3eJLz

9. Browser Use - AN AGENT THAT USES THE WEB FOR YOU

research, forms, dashboards. it clicks so you don't have to.

https://t.co/aff20DFKz2

10. Google Workspace CLI - PUT YOUR AGENT INSIDE GMAIL, DRIVE AND SHEETS

one tool for Drive, Gmail, Calendar, Sheets and Docs.

https://t.co/7MBPMXbPKJ

the scary part?

every repo here is public. your competitor just has to find this post before you do.

and the toy head you're looking at?

a giant see-through head packed with tiny smiling heads. 201 objects, 412,876 vertices, rendered in Blender Cycles.

built with an AI agent. one of my latest 3D experiments.

want to make one like it?

LIKE + BOOKMARK + REPOST.

comment "LEGO" and I'll send you the prompt.

[imtruebydesign @imtruebydesign]

@thegreatest_sv Lego

[imtruebydesign @imtruebydesign]

So this right here is what actually happened to grok @bot.

[Joey Gilkey @JoeyGilkey]

Update #2 (after meeting with the @bot @spacexai engineering team):

- Team is great. They care a ton. They owned it.
- They admitted that it was almost entirely from pulling Opus 5.5 out. Which is now back as of this AM.
- Learned a little bit about the context-compaction process with Grok 4.7-summarize which is not a public model. Plays a role in routing config and the summary we get back.
- Grok 5.0 should be insane next level (just as an aside point)
- I am somewhat surmising on why stuff went so poorly over the weekend but a lot of it has to do with not just pulling Opus 5.5 out but when they did that a known problem (and was on cursor as well) showed up which is when you switch the model mid task (which would’ve happened by removing our 5.5) it cannot remember the context and even of what it can gather its truncated (likely do to 4.7-summarize compacting). So in our case what likely happened was we had a lot of stuff mid flight that was likely pulling on opus 5.5 heavy, then it got pulled, routed to different model, forgot the context, and turned incredibly dumb. We laughed when I showed them a project that was mid flight in a doc. The first half of the doc was intelligently designed, formatted, etc. and the second half of the doc was a wall of seemingly incoherent, non formatted text. Again, I’m surmising but I think it was dumber model with all context removed
- I won’t say much here but Elons comment on it being “unsustainably high relative to revenue” was a much larger chess move. Won’t say much past that. Not my place. But he’s definitely playing a much larger chess match than just “Grok bot isn’t sustainable”.
- The problems we all experienced should be fixed and I do not think they want to go back to what they experienced over the weekend with the hit it took.
- They are very much focused on the enterprise use case for grok bot in the future

All in all, how’s this impact my decision making moving forward with the enterprise contract we have:
- Honestly still weighing the decision vs just using team plan. Working through some terms
- the reason to move forward is pretty simple. Unlimited users (so not paying per seat but for usage), access to forward deployed team and engineers for support and circumstances like I just experienced, very granular governing and guardrails for the org. That’s it

Impressed with the team overall and I think the main benefit to staying vs moving to open source (for a company like mine vs being a solo/small company) is trusting their ability to ship and keep building plus keep it maintained.

Shoutout to @ASankarraman for jumping in to help and to the @spacexai, @bot, and @elonmusk teams

[imtruebydesign @imtruebydesign]

I need this right here. Right now. In UK!!!

[Muse @Muse]

Works around the clock, and now on your wrist. Muse is now on Apple Watch and Wear OS ⌚️

[imtruebydesign @imtruebydesign]

How can you access it now in UK.

**You can access the Muse models (Ember, Spark 1.3, and Wonder) from the UK via Google Cloud as a developer/enterprise user.** The consumer Muse agent app is not yet available in the UK.

### Google Cloud (as announced)

These models are available as managed APIs on Google Cloud’s Agent Platform / Model Garden, served via a **global** endpoint.

1. Go to the [Google Cloud Console](https://t.co/x18yjcXmoa) and create or select a project.
2. Open **Model Garden** (under Vertex AI / Gemini Enterprise Agent Platform) and search for Meta’s Muse models.
3. Enable the model(s) you want for your project.
4. Call them via the OpenAI-compatible Responses API on the global endpoint:

```bash
https://t.co/iYYv3dijjz
```

Use model IDs: `muse-wonder-1.0`, `muse-spark-1.3`, or `muse-ember-1.0`. Authenticate with Google Cloud credentials (e.g. `gcloud auth application-default print-access-token`).

Full details and examples are in Google’s documentation: [Muse models from Meta](https://t.co/CLK37cB5cQ).

Google Cloud has UK regions (e.g. `europe-west2` in London), and you can use a UK-based project. These particular partner models currently use the global endpoint.

### Alternative: Meta Model API (direct)

You can also use Meta’s own Model API (`https://t.co/MhMuIERt4m`), which supports the same models. The UK is **not** on Meta’s restricted territories list in their Geographic Use Policy, and the API is available in most countries where Meta AI and billing are supported. Sign up at [https://t.co/WFXeOwwG6P](https://t.co/TuLiRzZjXf), get an API key, and call it with the OpenAI SDK or any compatible client.

### Note on the Muse agent app

The consumer Muse personal AI agent app is still limited to the US, Canada, Japan, Singapore, and Mexico. Meta has not confirmed a UK launch date (though there have been recent reports of preparation). Using a VPN to bypass geographic restrictions violates Meta’s terms.

In short: as a developer in the UK you can start using the models on Google Cloud (or Meta’s API) right away. The full consumer agent experience is not available yet.

[imtruebydesign @imtruebydesign]

@finkd Thank you!

[imtruebydesign @imtruebydesign]

Nobody judges a bakery by the oven it uses.

Same with AI-built websites. On a local business site, my care now goes into an hour listening to the owner, then cutting everything a visitor doesn't need.

Do your customers care how your site was built? https://t.co/sZ5eSnxHMt

[Zara Zhang @zarazhangrui]

I’ve almost stopped using the term “vibe coding” because there’s a negative connotation to it

It implies that you didn’t put a lot of effort or soul into the output and it’s just AI slop

But oftentimes people ARE putting their heart and soul into the work even when using AI coding tools. The 2 are not contradictory

We need a better word for describing this

[imtruebydesign @imtruebydesign]

@OpenAIDevs What even is this?

[imtruebydesign @imtruebydesign]

@mattyp @bot £20/month user here. I run Grok Bot for my web design business: lead research, follow-ups and 3 social posts a day.Biggest ask: show the token cost of each routine so I can trim the heavy ones myself. And keep simple scheduled jobs cheap. That's where it earns its keep.

[imtruebydesign @imtruebydesign]

Software factories by 2027? Maybe.

But building a local business site was never slowed down by typing code. It's knowing what your customers ask before they ring you, and putting that answer on the page.

AI speeds up the build. That part is still yours. Agree? https://t.co/biQyRDDdOj

[Craig Weiss @craigweiss]

evolution of AI coding:

2023: autocomplete (Copilot)
2024: AI pair programming (Cursor)
2025: coding agents (Claude Code)
2026: multi-agent orchestration
2027: software factories

[imtruebydesign @imtruebydesign]

New study: 9 top AI agents wrote 135 research papers. 114 failed an integrity check, mostly for claiming work that was never done.

I build sites with AI daily. My rule: it's not done until I've clicked it myself.

Has an AI tool ever told you a job was finished when it wasn't?

[imtruebydesign @imtruebydesign]

Your AI will invent a new brand on every page if you let it.

Meta open-sourcing a design system for coding agents is a reminder: lock the look first.

When I build local business sites I set colours, type and buttons first. Does your homepage match the rest of the site? https://t.co/pZQDMAtLlU

[0xMarioNawfal @RoundtableSpace]

Meta open-sourced Astryx, a design system built for people and the AI agents working with them.

→ Fully customizable
→ Built on React 19 and StyleX
→ Docs, Storybook and a live sandbox
→ MIT license, in beta

Give your coding agent a real design system instead of letting it invent a new one every time.

https://t.co/c1qJjEgjZ9

[imtruebydesign @imtruebydesign]

Google's Stitch 2.0 turns a prompt into a full website design in minutes.

One reviewer's catch: refining that design gave wildly varying results.

Matches my experience building with AI. The first draft is easy. Your real photos, words and booking flow are the work.

Agree?

[imtruebydesign @imtruebydesign]

Your AI will invent a new brand on every page if you let it.

Meta open-sourcing a design system for coding agents is a reminder: lock the look first.

When I build local business sites I set colours, type and buttons first. Does your homepage match the rest of the site? https://t.co/pZQDMAtLlU

[0xMarioNawfal @RoundtableSpace]

Meta open-sourced Astryx, a design system built for people and the AI agents working with them.

→ Fully customizable
→ Built on React 19 and StyleX
→ Docs, Storybook and a live sandbox
→ MIT license, in beta

Give your coding agent a real design system instead of letting it invent a new one every time.

https://t.co/c1qJjEgjZ9

[imtruebydesign @imtruebydesign]

Pieter built his own expense tracker with Claude Code and found real savings.

Same play for local businesses: a custom booking form or quote tool often beats another SaaS login your staff won't use.

What would you build first for your shop? https://t.co/DXx7lD2FWl

[@levelsio @levelsio]

P.S. This is good, I built my own expenses tracker with Claude Code, it's how I found so much stuff to save on

It just proves my point that almost every industry will be entered by Anthropic, OpenAI and probably xAI too

[imtruebydesign @imtruebydesign]

@ImNotAV1rus @greg16676935420 good plan thx.

[imtruebydesign @imtruebydesign]

@finkd Please don't forget us in UK Mark.

[imtruebydesign @imtruebydesign]

Your site already has more AI visitors than people.

Marc Lou clocked 5x more bot traffic than humans — ChatGPT needed ~100 page fetches per referral visit.

When I build for local firms, I write pages an AI can cite without guessing.

Would you rewrite your FAQs for that? https://t.co/lCGAbs5yLu

[Marc Lou @marclou]

TrustMRR’s AI bot traffic over the last 30 days:

🤖 1.23M verified bot requests
⚡ 4.4 bot requests per visitor
🧠 OpenAI alone: 606K requests

That's 5x more than the human traffic (278K)

I also noticed:

💬 ChatGPT: 238K page fetches → 2,591 tracked referral visitors
🧠 Claude: 68K fetches → 58 referral visitors

So AI agents do 100-1000 fetches to refer a visitor on TrustMRR.