Dennis (MaxLife) retweeted
Overjoy Storefront is now live. And it's free forever for brands signing up through November!
Custom buyer pricing, net terms, rep accounts, and native integration with Overjoy CRM.
Your entire wholesale business, in one place.
Dennis (MaxLife) retweeted
Hermes is great. Open Minis isn't bad either. 😇
🤖 Made with AI
You can use Hermes Agent for a lot more than flight booking. Here are 326 use cases from real users:
hermes-agent.nousresearch.co…
Dennis (MaxLife) retweeted
Live on YT Now
youtube.com/live/N-aHZFGNYdE…
Vibe Coding Everyday Until I Can Move Out of My Hometown - Day 7 - $0 Earned | Goal $10k/mo
Replying to @jule_power
@jule_power the charging station on the left side is out of service at Hilton Garden Inn, Palm Coast
55 Town Center Blvd, Palm Coast, FL 32164, USA
1
5
66
Dennis (MaxLife) retweeted
DeepSeek makes history again.
You no longer need to be rich to use frontier models.
The new DeepSeek V4 Flash 0731 is almost as intelligent as Grok 4.5 at a fraction of the cost. The current price on OpenRouter is $0.09 per million input tokens and $0.18 per million output tokens.
Before this release last week, the cheapest frontier model was Grok 4.5 at $6 per million output tokens, followed by GPT-5.6 Sol, Opus 5, Fable, and others at much higher prices.
DeepSeek sits around 50 on the intelligence index, while Grok is near 54. Only 4 points behind and roughly 97% cheaper.
But that's not all. This model is also a beast to run locally!
It's 284B total parameters with just 13B active per token. It's MIT licensed, has GGUF quants that fit on a 100GB+ machine, and people are already running abliterated builds for uncensored output, as well as fine-tuned versions.
You can download the official version and distilled ones from Hugging Face and run them locally, fully private and without paying for inference, using two NVIDIA DGX Sparks.
Running locally still requires a $6k+ investment, but if you want privacy and the freedom to run multiple versions, including uncensored ones, it's probably worth the cost for a model that delivers intelligence at nearly Grok's level.
This is now my main model for orchestration and agentic tasks across my multiple agents.
If you're paying for $100 or $200 subscriptions to Claude and Codex, you probably don't need to. Unless you're doing high-reasoning tasks, all you need is Hermes Agent running with DeepSeek.
At tuik, we make these and more advanced configurations for you. Have a look 👉 tuik.ai/
Dennis (MaxLife) retweeted
Just cancelled my Claude account.
It was a fun 2 years watching Anthropic create an excellent product... but at a certain point a man's got to look himself in the mirror and ask why he's paying a company he disagrees with on so many levels.
To replace this gap in my life, I'll be upgrading to the $200 Venice Max plan, to build mainly with Kimi, GLM, and Deepseek. I'll have less tokens to waste but at least my money will go towards a mission I believe in... Vote with your dollar, as they say.
I'll post updates to share how it goes.
Dennis (MaxLife) retweeted
10 more days to decide whether to cancel my Claude sub or not
First it was GLM 5.2, then Kimi K3, and now DeepSeek V4-Flash has begun its seduction of me
I have become genuinely curious to measure how far a $100 Venice sub with these models will take me vs $100 with the devil
Dennis (MaxLife) retweeted
Been going deep on AI filmmaking lately.
What strikes me the most fascinating is still somehow the least obvious:
Models like Seedance 2.0 are extremely adept at creating cinematic shots with smooth edits...
but without good references, you end up with characters, objects, locations, and voices all over the place, with inconsistencies so frustrating that you will want to give up.
(in the pic below, I needed a minimum of 6 reference photos just to get the scene's lay out right)
But it's fascinating to me because it's just like all other AI:
Context Context Context.
This is the big mindset shift: provide excellent context and be extra clear in your instructions, and this technology will work with you to create great things.
There's never been a better time to put your creative genius to good use.
[and shout out to all the AI filmmakers out there, I hadn't realized how tricky this was once you start trying to create full scenes...]
Dennis (MaxLife) retweeted
Today we are launching @boski on WhatsApp!
Boski is the most personal ai agent out there
It proactively learns about you and constantly thinks how it can help you save time, make better decisions and win harder
We are building Boski to be available on every possible platform
We shipped our mobile app a few weeks ago. We are launching whatsapp now. Web, imessage, X and a couple more are coming soon too
We are still in early beta but we are planning to open up soon
If you want to test Boski with us, please text the number from the video and join our early community (also on whatsapp)
See you there!
Dennis (MaxLife) retweeted
Not Sugar's favorite car getting stolen while he's casually playing snooker
And instead of panicking, this man stays calm as ever. Then Sasha Calle shows up like, "I can get it back for 500 bucks."
#Sugar
Dennis (MaxLife) retweeted
Trifecta x Hermes is a deadly combination. Keep an eye out soon for a bundled installation option :)
250 years of America today.
France raised me. Gave me my love of beauty, of community, of revolution itself.
America freed me.
It taught me to dream big and fail bigger. That failure isn’t the price of ambition, it’s the tuition.
After 15 years in the US, I went back to France to build. Gave it 3 years. Then I flew straight back to San Francisco. My gut knew: this is where you build.
France gave me my soul. America gave me my shot.
And yes, America has flaws. But that’s by design. This country experiments faster than anywhere on earth, and some experiments fail. That’s not weakness. That’s America paying its own tuition. It’s how it finds the right answers first, again and again, for 250 years.
People still cross oceans to get here. I was one of them.
Proud to be American.
Joyeux anniversaire 🇺🇸🇫🇷
Dennis (MaxLife) retweeted
Today is my birthday, (woooo…)
I’m 34 now.. damn I’m getting old.
Wish dad was here, he would have loved this AI thing.
Gotta keep building to make him proud, another year in the books 🫡
Hope your day is amazing ❤️
Dennis (MaxLife) retweeted
We're giving away an inference box to help democratize AI! Enter now for a chance to win unlimited tokens and unlock the future of AI. checkout OpenMonoAgent.ai to learn more
Every app I vibe code has the tech stack below
Easy for beginners and free to start
If you've never built an app before, just paste this list into Codex or Claude Code and you'll be good to go:
Web framework: NextJS
Hosting: Vercel
Database: Convex
Auth: Clerk
Payments: Stripe
Styling: Tailwind
AI: logic- OpenAI, creativity- Claude, cheap tasks- Gemini Flash 3
Emails: Resend
Design apps with: GPT image gen 2 + Claude Design
AI I use to build it all: Codex desktop app w/ GPT 5.5
Any questions let me know!


























