I call out big tech company bullsh*t, avoid hype, and show scaling companies how to grow with AI.
Share
where have you been?
Published 3 months ago • 4 min read
a braindump.
Hi Reader,
I disappeared for a while.
I’m sorry - late last year I joined a startup, then earlier this year went full-time contract on it with a high-risk, go big, or go home kind of bid.
We’re now in the latter stages of that bid and at the “omgwtf I’m not sure if this is going to work out” stage, and look: I got what I signed up for.
It’s been eye-opening and gratifying jumping onto the tools and building a growth engine for another business and if it doesn’t work it won’t be from a lack of trying.
I’ve been thinking about what I do with this humble little newsletter and I'm still marinating on it.
While that happens I'm sharing what is interesting to me at the moment.
Feel free to send anything my way you’re finding interesting too.
Sam Altman (OpenAI) started a blog that references energy consumption.
This reads like a bald-faced lie.And it is by focusing on the cost-per-query, not all of the work that goes into hosting the data centres, training the models, cooling them with water, and more.
Comparing them to an oven at one point of time is like saying you were singed by the one microsecond exposure to the explosion (while conveniently ignoring the fact that explosions go for seconds and do a lot of damage).
If you’re reading anything about AI (or you suspect is AI-generated) start by disagreeing and then consider evidence in its favour. You might call this critical thinking but it goes even deeper than that.
Something strange is happening to the Internet as a result of generative AI and just like showing a person broke the law, the burden of proof is going to become far higher than what we’re currently used to.
This is ultimately a good thing because historically (yes, even pre-Internet) misinformation has been dangerous and the cause of wars, famines, and misfortunes (see: The Crusades, Tulip mania, Spanish Flu)
One of my life hacks...
For frequently recommended books that I can't get into but know I need to is switching over to audiobook.
Donella Meddows A Primer on Systems Thinking was one of theses, and Yuval Noah Harari’s Sapiens is another.
The latter is what I want to talk about. I hated the narrator (it wasn’t Yuval, it was some pompous sounding Englishman).
But I still loved the content. I never took an interest in history in my younger years, and the book did an amazing job of breaking it down and explaining why I should be interested.
One of the ways Yuval hooked me in was frequently jumping back to the present to make everything that was being explained more relatable.
There’s a moment in the book that points to the French revolution and the obscene amount of debt their government was in.
Which made me think of what is going on in the US right now:
More debt than GDP
I'm beginning to think about what I do when I can no longer "do" marketing.
Professions as we know them today won't be around for that long.
This isn’t hype or fear-mongering - it just is.
I did a presentation recently on “Future Trends in AI” for the City of Monash.
There’s so much garbage out there that I wanted to provide something really grounded, practical, and yet future-facing to help the audience of business owners, consultants, and service providers who were curious about this stuff but not sure of where to focus.You can find the presentation here.
Despite all of the hype, there is something happening and its disruptive.
The Internet was disruptive.
Social media was disruptive.
Smartphones were diruptive.
This is the global adoption % average year on year of LLMs versus those three disruptive technologies:
I had to double and triple check these numbers, in defence of the first 3 - LLMs are a direct beneficiary of instantaneous distribution
Claude Projects is exceedinly good.
If you're going to pay for one subscription - I would make it Claude Pro/Max right now.
Projects gives you something that generic LLMs are terrible at: context.
Some of the things I’ve used it for:
Uploading background/notes/operating documents to determine “what next” for the startup I’m working with
Uploading libraries of .JSON workflows and cheatsheets for building automated workflows in n8n
I've written private journals (braindumps) for the last 10 years. I converted them from .docx to Markdown and gave these project instructions -
You are my expert personal and business growth coach. I am providing you with nearly 10 years of my personal and business journals, all in markdown format. For this project, your role is to help me maximise self-awareness, identify patterns, and accelerate my personal and business growth.
Then asked it to tell me things I might not know:
You’re actually exceptional at crisis management and reinvention. Your journals show you’ve navigated job loss, marriage breakdown, ADHD diagnosis, addiction recovery, and major life transitions while maintaining professional growth. That’s not instability—that’s adaptive resilience.
Your “job hopping” follows a predictable pattern that’s more strategic than you realize. You leave when you sense you’re not valued for your strategic thinking, but you consistently land in better positions. This isn’t career self-sabotage—it’s unconscious career optimization.
You have a rare combination of strategic thinking and emotional intelligence. Your ability to analyze business situations (like the UseVerb revenue projections) while simultaneously processing complex relationship dynamics shows executive-level cognitive flexibility.
Your resistance to authority isn’t about control—it’s about respect for your expertise. You don’t resist being told what to do; you resist being told HOW to do something you already know how to do well.
I would say I am aware of these sorts of things but nice to see it played back to me in such plain and succinct language and have my tyres pumped up.
–
That will do for today - I missed this.
Time has been short!
Being a parent of twins is hard - since they’ve become more mobile G and I spend most weeks just working and recovering.
We love it and are incredible grateful to be on this journey together - but that doesn’t make it any less exhausting some times.
Hello Reader, Great to be here again. This week I’ve been webinarring, discovering new toddler ailments from daycare, and did my first beep test run in a long time. But let’s talk AI. This week I look at: Some cool ways n8n is used for ADHD A newsletter deep dive and building in public Building an app with “vibe coding” tools There’s a lot to rock’n’roll with so let’s make like a shake and get steady 🥤 -Marshy Some cool ways n8n is used for ADHD I follow a lot of the n8n (an automation...
Hey fam, Is there anything happening in AI right now? Just kidding lmfao - that's stupid. But if you’re newish to this newsletter - welcome! I write about 3 topics each week usually centred around growth, impact, and strong opinions. This week we’re covering (checks notes): Hacking the press cycle Novel use case: interviewing your “ideal customer” for your website Building a lead generation machine with AI (another presentation) I’m keen as mustard to get into the meat of this, so let’s make...
Hi everyone, Welcome to another edition of AI versus Marshy. It’s been a week or so - and I'm kindof glad I haven’t said a single thing about GPT-5. Flex! Today we’re looking at: mental health doom-mongering a little nugget for the hackers on this list one-shotting landing pages and how to stay up-to-date with the webinar release schedule Alright - lots to get on with so let’s make like a knoll and step on it. AI versus mental health I’m passionate about mental health, and supporting people...