We build tools that save businesses time and money by helping them unlock their greatest potential and achieve growth through data and AI-powered solutions.
Houston, TX
- Tweets 233
- Following 12
- Followers 146
- Likes 317
Pinned Tweet
AI is useful today. The money behind the frontier is harder to read. Our new research follows the circular deals linking AI labs, chipmakers, cloud providers, and data centers. Who is paying for the AI boom?
digitalmeld.io/blog/who-is-p…
1
6
756
Digital Meld retweeted
Tomorrow at Texas Venture Fest Houston: I'm on the AI Developer Ecosystems panel at 1:40 PM CT, 17th floor of The Innovation Hub. Hot off my return from OpenAI DevDay we'll discuss how developers are actually building with AI agents. If you're near downtown Houston, come say hi! luma.com/texas-venture-fest-…
2
12
434
Digital Meld retweeted
IAH ➡️ SFO for OpenAI Dev Day, let’s go!!! Follow along at where.bradgroux.com.
3
2
22
781
Digital Meld retweeted
I’m heading to San Francisco for OpenAI DevDay this week, thanks to @OpenAI!
I’m looking forward to meeting a ton of brilliant people and hearing what OpenAI has coming next. My schedule includes sessions on agent architecture and Codex, plus a couple of meetups before DevDay. And if the rumors about a wearable announcement pan out, I’ll have even more to talk about. Can’t wait!
I’ll be sharing live updates here on X, and at where.bradgroux.com (where you can also see my full schedule) throughout the trip.
I’m in San Francisco from September 28–30, so if you’re around and want to meet up, please reach out. I’d love to hear what you’re working on.
3
2
24
23,880
Digital Meld retweeted
My trip is fully set and booked for OpenAI DevDay next week in San Francisco! I'll be there Monday morning through early evening Wednesday if anyone would like to meet up.
Keep track of me while I'm on the ground at where.bradgroux.com. Thanks to @OpenAI for having me!
Can't wait for DevDay next Tuesday.
Some really fun stuff, but also many many things that should change the way you work. It's been our most ambitious sprint and Astra has really made new things possible in such short amounts of time.
3
2
11
1,008
Digital Meld retweeted
I’ve been complaining about GPT-6 Astra, but I've been using it wrong. I was asking Eisenhower to storm the beaches of Normandy himself. Now Astra plans, delegates to 3-5 Sol threads, and reviews the work. Here’s what changed, plus three prompts to try.
32
11
235
310,438
Digital Meld retweeted
Looking to onboard your credentials to Muse? Unfortunately, there is no way to bulk import credentials from iCloud Keychain or 1Password into Muse (that's by design), but you can semi-automate the process pretty quickly. Full details in the tweet below.
Just tell Muse what service you need in chat and it'll pop a secure entry card, tap it, paste the key, done. The secret goes straight to the vault and never touches chat.
No Mac required. The cards render right in the Muse iPhone/iPad app, OAuth connects just open the provider's sign-in page, and iCloud Keychain or 1Password autofill works inside the secure form (I do it via 1Password). iOS suggests the matching login when you tap the field, one tap fills it. Seconds per credential.
Unfortunately, OS won't let any app bulk-import from Keychain (Apple only exposes it via AutoFill), and there's no zero-touch setup. Closest thing to bulk is giving Muse your list of sites so it can queue a secure card per site, and you tap through them rapid-fire with AutoFill filling each one.
Each card still needs your tap, the sign-in, the consent, and the vault approval. Apple likes the Human in the Loop, apparently. I was able to go through about 30 credentials from 1-password in about 10 minutes. Hope this helps!
1
2
8
1,057
Digital Meld retweeted
I kept hitting the same dumb problem: I wanted to feed YouTube videos to my AI via Codex, Muse, OpenClaw, Buzz, and every route was annoying.
Paste a link and pray the agent can fetch it. Watch it burn thousands of tokens pulling the page, choking on markup, or failing outright. Or install some bloated extension full of popups, accounts, and analytics phoning home.
So I built the thing I actually wanted: Minimal Transcript.
Tiny Chrome extension. Open any YouTube video, click the icon, get the transcript, TXT, Markdown, SRT, or VTT, timestamps optional. One click. That's the whole product.
Why it saves tokens: your agent starts from clean text instead of spending a fortune figuring out the video itself. No fetching pages, no parsing HTML soup, no hallucinating what was said. Paste transcript → ask your question → done. On a 3-hour video, that's the difference between a few thousand tokens of clean captions and tens of thousands of wasted ones.
Details I sweated because they matter:
• Prefers real captions over auto-generated when both exist
• Strips YouTube's hidden screen-reader junk ("0 seconds", "1 minute, 5 seconds") that pollutes naive scrapes
• When YouTube gates the download endpoints, it falls back to driving YouTube's own transcript panel, works whenever YouTube's panel works
• Remembers your format; copy-to-clipboard if you don't even want a file
• No popups, no ads, no accounts, no third-party servers. Private by design. MIT licensed.
• Free, sideload in under a minute: github.com/BradGroux/youtube…
If folks like it, I'll get it up on the Google and Edge extension stores soon.
18
2
47
34,895
Digital Meld retweeted
After reading @pvncher’s guide, I asked Astra in Codex to audit my workspaces. I revisted approval rules, consolidated skills, and cut skill-description text by 78%.
I share the changes, with prompts and code examples you can use to audit your own setup.
2
2
6
25,563
We love to save our clients money with AI 😃
Kimi-K3 with High Reasoning on Ollama Cloud running in Codex is fantastic at scraping your content.
If you run a SaaS and you charge an arm and a leg for people to access their own data via API... your days are numbered. This is going to save our client thousands of dollars.
1
97
Digital Meld retweeted
We're now officially @OpenAI Partners at @DigitalMeld, and I've just completed my OpenAI Consultative Solutions Practitioner certification.
3
4
20
1,030
Digital Meld retweeted
Did you know that you can now have up to five Ollama Cloud models available to you in Codex? Update your Ollama app, configure your five models of choice, and restart the ChatGPT app! That's it.
20x ChatGPT Pro and an Ollama Cloud Max plan are a dynamic duo. Astra and Sol along with Kimi-K3, GLM-5.3, Gemma4, and DeepSeek-v4-Flash is a hell of a toolset, all in one amazing harness.
I just had Kimi-K3 pick up on a project that Astra started, without issue - it just works. Kimi read Astra's history directly from the Codex workspace and picked up where it left off.
Seriously, if you're hitting usage limits with Codex and Astra, grab @ollama cloud as a backup. Their $100 Max plans are a steal and open for signups again. ollama.com/pricing#max
ALT Ollama cloud models in ChatGPT and Codex.
18
8
52
29,706
Digital Meld retweeted
Way more detail, numbers and charts in the published study - go.sstb.ai/astra-study
1
2
7
748
Digital Meld retweeted
My GPT-5.6 workflow hasn’t carried over reliably to GPT-6 Astra. I reviewed six days of records to understand why I kept repeating instructions. Here’s what I found—and what I still can’t explain.
47
5
98
246,289
Digital Meld retweeted
AI progress is accelerating, and safety has to advance with it.
I joined @BradGroux and Robert Groux on @DigitalMeld’s Start Small, Think Big to discuss why we need to engineer for safety while continuing to push the boundaries of what AI can do. piped.video/shorts/Pp1AE6cNg…
1
3
74
Digital Meld retweeted
There is some pretty wild information about GPT-6 Astra in my findings. Usage over six days was nearly 4 billion tokens across more than a dozen projects.
The article with full details will be out in about 3-4 hours.
I've found the issue with GPT-6 Astra and why it is so terrible working with guardrails, SOPs, and guidelines. The issues seem to arise from its assigning of subagents. Details are getting lost in translation - like a game of telephone with agents.
Working with an SOP, PRD, docs, guardrails or guidelines? Force the agent you are interacting with to do the actual work. I'll make a full evidence-backed post tomorrow with what I've discovered, and all of the frustrations (and wins) I've had with Codex and Astra tomorrow.
I'd do it now, but I'm about to pull my hair out.
4
3
29
5,798
Digital Meld retweeted
While I've had some issues with GPT-6 Astra following PRDs and SOPs (I'll figure it out), I have had an amazing experience with Astra and @threejs!
I've been working on a synthwave-inspired city builder, with fully customizable (built with blocked layers) and sharable building and vehicle designs.
I started off trying to provide it with a massive PRD, and it didn't go so well, so I've started with a smaller prompt and have been doing iterative improvements as we go.
What you see here is less than 40% of a $200 ChatGPT Pro plan weekly limit, with GPT-6 Astra on Medium settings (about seven hours total).
I did a quick POC between Blender/Unity vs three.js, and quickly chose three.js, because you can see the improvements in-browser immediately.
What a time to be alive.
1
3
8
20,755