@AWSCloudIndia@awscloud
Urgent assistance needed. Our AWS account remains restricted despite securing compromised credentials and completing remediation. 150+ team members are impacted, and 10,000+ users are at risk if production recovery is needed. Case ID: 471112538523
i can't believe nobody caught this.
Anthropic's entire growth marketing team was just ONE PERSON
(for 10 months, confirmed)
a single non-technical person ran paid search, paid social, app stores, email marketing, and SEO for the $380B company behind claude
here's exactly how one human is doing the job of a full marketing team:
it starts with a CSV.
1. he exports all his existing ads from his ad platforms along with their performance metrics (click-through rates, conversions, spend, etc)
2. feeds the whole file into claude code
3. and tells it to find what's underperforming.
claude analyzes the data, flags the weak ads, and generates new copy variations on the spot
this is where he gets clever:
he then splits the work into 2 specialized sub-agents:
1. one that only writes headlines (capped at 30 characters)
2. and one that only writes descriptions (capped at 90 characters).
each agent is tuned to its specific constraint so the quality is way higher than cramming both into a single prompt
so now he's got hundreds of fresh headlines and descriptions.
but that's just the text.
he still needs the actual visual ad creative, the images and banners that go on facebook, google, etc.
so he built a figma plugin that:
1. takes all those new headlines and descriptions
2. finds the ad templates in his figma files
3. and automatically swaps the copy into each one.
up to 100 ready-to-publish ad variations generated at half a second per batch.
what used to take hours of duplicating frames and copy-pasting text by hand
so now the ads are live.
the next question is which ones are actually working.
for that he built an MCP server (basically a custom integration that lets claude talk directly to external tools) connected to the meta ads API.
so he can ask claude things like:
• "which ads had the best conversion rate this week"
• or "where am i wasting spend"
and get real answers from live campaign data without ever opening the meta ads dashboard
and the part that ties it all together and closes the loop:
he set up a memory system that logs every hypothesis and experiment result across ad iterations.
so when he goes back to step one and generates the next batch of variations...
claude automatically pulls in what worked and what didn't from all previous rounds.
the system literally gets smarter every cycle.
that kind of systematic experimentation across hundreds of ads would normally need a dedicated analytics person just to track
the numbers from the doc:
ad creation went from 2 hours to 15 minutes. 10x more creative output.
and he's now testing more variations across more channels than most full marketing teams
a $380 billion company.
and their entire growth marketing operation (not GTM) = just one person and claude code lol
truly unbelievable
This is exciting; I expect we are going to see a lot more things like this and it will be one of the most important impacts of AI. Congrats to the Future House team.
https://t.co/Cxeh8UlWdk
I have tried using ✨ `Nvidia/Llama-3.1-Nemotron-70B-Instruct-HF` (Open source models finetuned on Llma-3.1-70B)
on 🤗Huggingface chat, and the outputs were amazing.
1. Content generated by it is non-AI detectable
2. Thinks through all the aspects.
Just like a WOW 🤩
So much customization of @chartjs 🤯
1. Spreaded Area Chart
2. Stepped Line Chart with offset for signal representation.
3. Scale customization with dynamic value rendering
I built a hedge fund team of AI agents.
All using @langchain and LangGraph.
This team has 3 analyst agents:
1 • fundamental analyst
2 • technical analyst
3 • sentiment analyst
Fundamental analyst has access to financial statements and analyzes fundamentals.
Technical analyst has has access to stock prices and finds pricing patterns
Sentiment analyst has access to options, insider trades, and news to gauge sentiment.
This is just the first iteration.
Eventual goal is to model real-world hedge funds.
I just updated my Bento profile and it’s so cool! Life is about stepping out of our comfort zone, trying something new, and taking a chance to make tomorrow better than today.
https://t.co/AVYIsvT8KJ
🚀 Excited to launch my portfolio website! Check out MilanByte Tech for insights on backend development, data tools, and automation. Let's transform ideas into reality and drive business growth together! 🌐💡 #PythonDeveloper#TechInnovation#Freelance
👉 https://t.co/EZt9dVrVhL
Engineering { Something Crazy }: 📉
🛒 A fully automated system that captures daily prices from major retailers like Amazon and Walmart.
🕵️♂️ We're not stopping there! We also track prices from third-party sellers to spot any price manipulations.
#TechForGood#Innovation#data
@Anshul_439 Bro, but your certificates and your projects are not aligned with each other if there anything in private please share it with us that will also rock 🥂🤝
Preparing for first user insights for the my SaaS product which helps product managers to decide their next features and know their product very well #buildinpublic