We help professional trades, and regional service businesses grow with proven digital strategies.
Coffs Coast
Joined May 2015
- Tweets1.8K
- Following303
- Followers35
- Likes4.1K
Ian Mackenzie retweeted
Every social and video platform wants more shorts and they’re willing to pay for them:
1. YouTube Shorts get 200 billion views a day
2. X is paying creators up to $5,000 to post shorts
3. I know ppl making five figures for posting a sponsored short
The problem is most people have no idea how to make good shorts.
That’s why I built /video-short to let anyone turn a raw solo recording into a polished short. It finds B-roll for you and comes with a review page that makes it easy to give AI feedback on any frame.
📌 Install my /video-short skill for free:
github.com/petergyang/video-…
If you find it useful, please ⭐ the repo so more people can find it.
📌 Watch my tutorial on how to use the skill:
youtu.be/NWll-9p84b4
AI has become amazing at video editing, but most people still don’t know where to start.
Today, I’m introducing /video-short, a free AI skill that lets anyone turn a raw recording into a polished short.
/video-short works with your favorite AI agent to add:
→ B-roll footage
→ Motion graphics
→ Captions
→ AI video and music
It even comes with a simple review page to let you give feedback to AI on any frame until the short feels just right.
📌 Get /video-short for free on GitHub:
github.com/petergyang/video-…
If you find it useful, please ⭐ the repo so more people can find it.
📌 Watch my full tutorial on how to install and use the skill: youtu.be/NWll-9p84b4
Ian Mackenzie retweeted
Codex is amazing for 3D printing.
And Bambu Studio runs in the Dots VM which makes it even more fun.
Workshopping a mini version of a house with the 3D printer.
Parts all made by my trusty @ChatGPT Dot.
Ian Mackenzie retweeted
🚨 Google lost power in London this morning and Revolut, a bank with 80 million customers, went down with it.
I've spent the morning reading what Revolut users went through. It's wild.
People stranded at petrol stations, unable to pay for fuel or a taxi to the airport.
One traveller couldn't get out of a train station in Japan.
A 71-year-old woman stood at a supermarket till for an hour. Her kid had to drive 30km to bring her cash.
Card payments, transfers, ATM withdrawals, currency exchange, share trading. All down.
Revolut's statement said "all our customers' money and data are safe."
Safe. You just can't touch it.
Google's explanation so far is a "power event" in one zone of its London cloud region. Its advice to affected customers was to move their workloads to another zone or region "if feasible."
Must be nice. Revolut customers couldn't even move £10.
In July the UK government put Google Cloud, AWS, Microsoft and Oracle under direct Bank of England oversight, because one outage at any of them could shake the entire financial system.
12 days ago the Bank of England ran a drill with the UK's 38 biggest banks and market operators. The scenario they practised was a global cloud outage.
And exactly one year ago today, AWS went down and took Lloyds and Halifax with it.
Same date. Different cloud. Lloyds was having problems again this morning.
Revolut spent five years earning a UK banking licence.
Bitcoin has been running for almost 18 years. It doesn't have a London region.
Ian Mackenzie retweeted
Our latest model advances bring stronger capabilities for building and migrating software in low-resource programming languages such as COBOL, Fortran, and Visual Basic.
These languages power software that banks, governments, and businesses depend on. Progress here means understanding decades of business logic and helping developers modernize those systems while preserving what works.
We’re building these capabilities around the challenges developers and enterprise customers bring us. If your team is working on these systems, tell us which languages and workflows we should tackle next.
openai.com/index/low-resourc…
Ian Mackenzie retweeted
James Burke's perfectly timed shot on television in 1978 is hailed as one of “The Greatest Shot In Television History”
Ian Mackenzie retweeted
Do PRO code review with GPT-6 Pro.
It can use GitHub plugin and do it in less time by doing more in parallel.
Ian Mackenzie retweeted
Design Tokens are now available in GenerateBlocks Pro 2.8. Define your colors, fonts, and spacing in one place, then use them across blocks, Global Styles, and patterns. Whether you've been using Global Styles for a while or are just getting started, this guide helps you get up to speed on the new features.
generatepress.com/design-tok…
Ian Mackenzie retweeted
GenerateBlocks Pro 2.8 is fully released. Make sure you also update GenerateBlocks to 2.5. For details on what is included, refer to the post below. generatepress.com/generatebl…
Ian Mackenzie retweeted
GenerateBlocks Pro 2.8 (and GenerateBlocks 2.5) launched yesterday: Design Tokens, a new Design panel, new dashboards, and one cohesive system. Here's the vision for where GeneratePress and GenerateBlocks are, and what's next.
generatepress.com/generatebl…
Ian Mackenzie retweeted
We discovered a sophisticated recording device that was hidden inside one of our offices. We used our models to understand the device and where it had come from, identifying that a specific employee had planted it a few days earlier. We referred the matter to the FBI, and we’re grateful to the agents and prosecutors who moved quickly to make an arrest. The FBI’s investigation is ongoing and we will continue to support their work.
At this time, we have no indications of this individual inappropriately accessing or exfiltrating model weights, source code, or customer data. The employee was terminated.
We take protecting our technology, data, and people seriously, and as a matter of national importance. Our security program is designed to protect against a wide range of threat actors, from insider risks to cybercriminals to nation states, and this case is an example of how AI can help address these sophisticated security threats.
Ian Mackenzie retweeted
Your Apple developer account could be banned soon, so here’s what to avoid (bookmark this one)
- Fake urgency. Win-back offer with a fake timer
- Review prompts in onboarding (Apple is cracking down on this one)
- Showing the weekly price bigger than the yearly price (for a yearly sub)
- Not having an updated terms & conditions
- Submitting the same build to Apple multiple times
- Using language like “no commitment - cancel anytime” for an upfront payment
Not worth getting your app delisted and payments frozen. Please be careful
Ian Mackenzie retweeted
With the current Codex reset frenzy, I've unleashed Astra 6 on Ultra and it is blowing my mind with some really incredible work. Use these prompts:
1. "Examine this project thoroughly, looking for bugs. Treat it as an adversarial review using as many subagents as you want. When an issue comes back, double-check it's correct, and add checked issues to a list."
2. "When all agents have finished, walk me through each issue one at a time, giving me reproduction steps so I can verify."
3. "For all bugs I report as verified, write a failing test proving the bug exists, fix the issue, check your work carefully, then run the test again to verify it's resolved."
It's found 43 issues so far, only 2 of which I disagreed with. Some minor, yes, but some big ones too 🙈
Ian Mackenzie retweeted
Talent only gets you so far.
Being good at something doesn't make you a profitable business.
• random thoughts people can't relate to
• big audience that never buys
• great work nobody sees
Talent gets you started. A personal brand gets you chosen.
Build the skill. Then build the trust that sells it.
Ian Mackenzie retweeted
🚨 "o" Update
OpenAI's always-on agent, their answer to Grok Bot/Muse, spotted in chatgpt.com's code
Coming to all Pro tiers, not locked to Pro Max • Codex Plus excluded • Fast Mode confirmed • Could launch as early as Thursday?
Ian Mackenzie retweeted
🚨 OpenAI Set to Reveal a Long-Term Agent at DevDay
- Codenamed "Aeon" — built for long-running tasks, similar to Grok Bot or Manus, working for hours, days, even weeks
- Likely built on Astra, already strong at long-horizon work
- Runs in a cloud environment like Cursor — sets everything up remotely and keeps grinding until the task's done
- OpenAI already has the infra (hosted sandboxes, multi-agent workflows) to make this the natural next step
- Rumored to support multiple agents collaborating on the same task — if real, that's a big deal
