Thomas Lancer
153 posts


Clawdbot + Kling = 550 videos per day
No actors.
No products in hand.
No ghost creators.
No missed deadlines.
Just viral TikTok Shop sales — 24/7.
Here’s the crazy part:
This system produces 550+ cinematic, product-ready ads per day from a single prompt.
And it feels exactly like running Facebook Ads in 2008 — except the CPMs are even lower, and the entire loop is organic.
Here’s how the AI Creator Agent System works 👇
Each Agent runs its own TikTok Shop profile and handles an entire growth function:
• Trend + angle research using Kalodata
• Competitor ad cloning (paste their ad → pick an avatar → regenerate)
• Automated creator outreach with Fastmoss
• Daily content generation using Kling or arc ads
• Localization, repurposing, and multi-format output
• Compliance cleanup + optimization
• Automatic posting across a Multi-Platform Swarm (hundreds of agents)
No touchpoints.
No delays.
No human bottlenecks.
Just a decentralized force of AI + UGC creators selling while you sleep.
Real results:
• $0.10 CPMs
• Thousands of organic views daily
• content that is realistic enough to actually increase sales
This is the Creator Agent Method: a plug-and-play system that replaces entire creative teams and launches content at a speed humans simply can’t compete with.
I packaged all the AI V2 workflow so you can deploy the exact system for your brand.
Comment AGENT and I’ll DM you everything for free.
(Deleting soon)
P.S. Repost for early access to the complete agentic influencer stack

English

This cold email system generated $23M in qualified pipeline for 18 AI SaaS companies last year.
This will stop your team from burning 1M$+ on cold email.
I've spent 3 years perfecting the exact cold email system that's generated over $1 billion in pipeline across hundreds of campaigns.
→ Inbox setup & deliverability (never land in spam again)
→ Signal-based list building (target buyers ready to buy)
→ 9 proven email templates that convert
→ Follow-up sequences that get 80% of replies
→ Performance benchmarks & tracking metrics
→ Complete tech stack breakdown
The results speak for themselves:
- 15%+ reply rates consistently
- 2%+ meeting booking rates
- <0.5% bounce rates
- Scaled to 20K+ emails/week profitably
This is the same framework used by top B2B companies to book 30+ qualified meetings per week.
I'm giving away the complete playbook with:
✓ Every template we use
✓ Full tech stack setup
✓ Step-by-step launch checklist
✓ Deliverability rules that actually work
Reply "cold" + follow and I'll send you the full Cold Email Playbook
English

@FoundersPodcast Have you read Revolution in the valley? Andy hertzfeld wrote it. first person account of the making of the Mac.
Also he has a site called folklore (dot) org with a bunch of stories from the Mac team themselves. V cool
English


@ericzakariasson @cursor_ai specific files - anytime its touching DB model files include the rule on SOP for running alembic migration
also for all .tsx files have a rule that tells it to separate business logic from UI code since it loves combining everything into one file if you don't prompt it not to
English

do you use "Apply Intelligently" or "Apply to Specific Files" in @cursor_ai ? if you do, what's your use case?

Michael Feldstein@msfeldstein
Do people find value from the advanced features in the Project Rules system in cursor (globs, agent fetched, etc) or would drastically simplifying it to nested AGENTS.md files be 95% as good and much easier to grok?
English

@layer07_yuxi what paper/book etc is the original quote from? looks interesting
English

Hinton ~1983 thought Boltzmann Machines > backprop, but debugged himself out of the infatuation
Boltzmann Machines failed to learn, so he printed out weights, 8 cm thick, and inspected them for weeks
it's the dreaded local minimum
so 1 yr later, in desperation, he tried backprop


djcows@djcows
always manually read the weights of your LLM to make sure he's unbiased
English
Thomas Lancer retweetou

xAI has exactly 0 available SOTA models
not a single company on the planet uses Grok because they don't even have an API for Grok 3
Anthropic is valued 20B lower than xAI:
but actually has available SOTA models and has shown that they can produce multiple competetive models, super strong revenue growth, ~1B revenue in 2024
*Walter Bloomberg@DeItaone
ELON MUSK: XAI HAS ACQUIRED X IN AN ALL-STOCK TRANSACTION, VALUING XAI AT 80B AND X AT 33B
English

one interesting way to improve performance on coding w/LLMs is to have it generate 3-5 responses at same time then have another model review it's answers and select best one (or ideally be able to test all it's solutions in parallel somehow and choose the one that works)
i find myself doing this already when solving bugs
i'll open 3 grok windows w/think mode, 2 o3-mini-high windows, 2 o1-pro windows and paste the file and context in all of them
oftentimes 2-3 out of the 7 will solve the issue and the other ones won't
English

@shaoruu @cursor_ai Being able to direct the apply model based on line number. In files over 1,500 lines it really struggles to find right spot to apply but if I could give the specific line numbers to start at or it could figure that out on it’s own would make the apply model way more accurate
English

what's one thing you really want added to @cursor_ai composer, or just to cursor in general? open to all kinds of ideas :)
English







