Pinned Tweet
Bye Bye ChatGPT
Nvidia just launched Chat with RTX and it's free for everyone.
Here are the details (+ how to download):
Aurora retweeted
I run a daily AI newsletter.
Half my job is checking what launched, changed, or repriced.
Every. Single. Day.
Claude is great at writing and answering questions.
But that research part?
It needs live web data.
So when I saw this webinar, I signed up right away.
Because it shows how to make Claude…
↳ Track competitor prices
↳ Research the live web
↳ Automate your weekly updates
Most of it without writing a single line of code.
It's a FREE webinar by Decodo 👇
🚀 Chat, Automate, Build: Powering Claude with Live Web Data
In just 30 minutes, you'll learn how to give Claude live web data…
And turn repetitive tasks into automated workflows.
Here's what they'll cover:
🔹 Live web research
Ask Claude to find and compare up-to-date info from the web.
🔹 No-code automation
Turn competitor price checks into scheduled spreadsheet updates.
🔹 Custom AI tools
See how Claude Code can help you build tools powered by live web data.
🔹 Live demos
Real workflows in Claude Chat, Cowork, and Claude Code.
Plus a live Q&A with Michael Gu (Boxmining, Superbash) and Robertas Lisickis (Decodo).
📅 November 19, 2026
⏰ 11:00 AM EST
🎟️ Free to attend
And a bonus for those who show up…
Attendees get an exclusive discount code for Decodo's Web Data API.
Developer, marketer, or just tired of repetitive work?
This one's worth your 30 minutes.
🔗 Leave your email here to get a reminder before it starts:
decodo.com/webinars/claude-d…
Less manual research.
More time for the work that matters.
Aurora retweeted
Coding agents got fast.
Reviewing their work didn't.
That's the real bottleneck now.
@jetbrains just shipped Air in IDEs.
Built right into the IDE.
Here's what makes it interesting 🧵
Aurora retweeted
I use AI video tools every day for my content.
Dubbing has always been the weak link.
The audio gets translated.
The face doesn't.
So the result looks like a badly dubbed 90s movie.
VEED just shipped a dubbing API that matches the speaker's lips to the new track.
That's the part that matters.
✅ Background audio preserved
✅ Tone and emotion intact
✅ A hint of the original accent still there
If you're building anything with video…
This is how you go multilingual without re-shooting a thing.
🤝 Paid partnership
Aurora retweeted
1. Your PM finds a tiny bug. 🐛
2. Your designer wants to fix an empty state.
3. Marketing needs one line of copy changed.
And somehow…
All 3 end up waiting in the engineering queue.
What if they didn't have to wait?
Base Code by @base44 fixs it.
↳ Connect your existing GitHub repo
↳ Describe the change in plain English
↳ Preview it on the real product
↳ Send it back to engineering as a standard PR
The important part:
🔒 Engineering still controls what ships.
Every change happens on an isolated branch, and your existing review process + protections stay intact.
So product, design, QA, or marketing can actually make the change — while engineering still decides what goes live.
🎁 30 days free right now.
One invite covers the whole team.
I also have a coupon for the first 50 users.
DM me and I’ll send it over.
🔗 base44.com
Aurora retweeted
I just found out US listeners spend 170 minutes a day on Pocket FM.
For comparison, TikTok gets 53.8 minutes a day.
That’s a wild gap for an audio-only app!
Here's how they do it:
- You listen to a few episodes free.
- The story leaves you on a cliffhanger.
- You buy coins to unlock what happens next.
Every episode gives Pocket FM another chance to learn:
↳ Where listeners lose interest
↳ What keeps them listening
↳ When they’re willing to pay to continue
Now it’s bringing those insights to writers.
It’s called Sherpa, an AI writing partner built for storytellers.
Pocket FM says it’s trained on 100M+ hours of listener data, including episode retention, coin spending, and drop-offs.
As someone who creates content, that’s what caught my attention.
Getting someone to start a story is hard. Keeping them interested through an entire season is a different challenge.
Sherpa helps writers take a single premise and develop:
↳ Characters and their motivations
↳ Story arcs and episode structure
↳ Punchier dialogue and stronger conflict
↳ Cliffhangers that leave something unresolved
Think of an idea like:
"A delivery driver recognizes his missing sister in a billionaire's family portrait."
Who took her?
Why is she there?
Does she remember him?
There's a whole season hiding inside those three questions.
Sherpa helps you develop it into something you can actually write from.
If you've had an idea sitting in your notes for years…
This is the week to open that file.
Check it out today: pocketfm.com/sherpa
Aurora retweeted
I use AI coding tools a lot, and I love them.
They’ve made building apps faster and easier than ever.
But there’s one thing I hate:
Watching the token counter every time I give an agent a bigger task 😅
“How many credits is this going to burn?”
I find that pretty limiting.
Then I found out about Junie Local.
It lets you run the full Junie coding agent directly on your Mac.
→ No tokens
→ No usage limits
→ Works offline
→ Your code, prompts & diffs stay on your machine
Just run /local inside Junie.
It downloads the model, starts the local server, and switches to local mode.
It currently runs Qwen3.6-27B at 4-bit, optimized specifically for Junie.
The most interesting part for me is unlimited usage.
That means you don’t have to worry about burning credits on things like:
→ Refactoring multiple files
→ Adding missing tests
→ Dependency upgrades
→ Framework migrations
→ Exploring an unfamiliar codebase
→ Long, repetitive coding tasks
You can just hand them to an agent without constantly thinking about credits.
One catch:
It currently requires an Apple Silicon M5 Mac with 64 GB RAM.
Still, I really like where this is going.
Local AI + unlimited usage is a pretty interesting combo for coding agents.
If you have compatible hardware, try it yourself:
junie.jetbrains.com/local
Aurora retweeted
Vibe coding changed how we build software.
Now a Swedish AI startup thinks the same thing is about to happen to the entire computer.
They call it **Vibe Computing.**
Instead of:
→ opening apps
→ clicking through menus
→ copying and pasting
→ switching between tabs
→ typing everything yourself
You hold a key and just say what you want done.
The AI handles the execution across your computer.
That's what Incredible is building.
And they just announced $2.5M in pre-seed funding, backed by investors with links to Anthropic, Lovable and Legora.
The interesting part to me:
We've spent decades learning how to operate computers.
AI might flip that relationship.
You tell the computer the outcome.
The computer figures out the interface.
Vibe coding might have just been the beginning.
Try Incredible: incredible.one
Aurora retweeted
Okay I have to talk about this.
My whole coding workflow runs on one tool now:
↳ Full-repo refactors
↳ Migrations
↳ Multi-file debugging
I hand it the task, walk away, come back… done.
It's called Qoder. And it just got absurdly cheap!
Here's why I'm hooked 👇🧵
Aurora retweeted
I cloned myself last week.
Not metaphorically. I built a version of me that writes LinkedIn posts.
Same hooks. Same line breaks.
Same "No fluff. No filler." rhythm I've used to grow to 200K followers.
Here's how it started.
Everything I know about writing posts that stop the scroll…
It lived in one place.
> My head
Which means it stopped the second I logged off.
No posts on my day off.
Nothing while I slept.
My "value" had an on/off switch.
So I handed all of it to a Sintra helper.
The openers. The pacing.
The CTAs that drive saves instead of empty likes.
Two years of pattern-spotting, handed over in an afternoon.
And now there's a second me.
You give it a rough idea — a tool you found, a lesson, a hot take.
It gives back a post in the exact format I actually use.
The clone doesn't sleep.
Doesn't get tired.
Doesn't stare at a blank screen at 2am.
It just… writes like me. When I'm not even there.
And the wild part?
It's stupid easy to build.
You can spin one up in under 5 minutes.
Here's the 4-step process:
↳ Step 1 — Sign in to Sintra: playosinc.pxf.io/L0mzva
↳ Step 2 — Click Helpers > Create Helper
↳ Step 3 — Give it instructions in plain English (pro tip: drop in samples of your work)
↳ Step 4 — Save it. Watch it write like you.
Anyone can do this now.
Whether you're into business development, customer support, SEO, or just need a virtual assistant…
You can clone the part of you that does the work.
Your knowledge stops working the moment you do.
This doesn't.
Check it out: playosinc.pxf.io/L0mzva
Aurora retweeted
Claude quietly dropped 13 free AI courses (with certificates)
No $500 course needed.
No “guru” required.
Just real skills — straight from Anthropic.
Here’s what you can learn 👇
Aurora retweeted
6 PROMPTS TO LEARN ANYTHING USING CLAUDE.
Most people use Claude to get answers.
The smart ones use it to build understanding.
Big difference.
One makes you dependent.
The other makes you dangerous.
Here are 6 Claude prompts that turn any topic into mastery👇
Aurora retweeted
Instead of watching Netflix this weekend.
Spend 2 days mastering Claude for free.
No $500 course needed.
No “guru” required.
Just real skills — straight from Anthropic.
Here’s what you can learn 👇
Aurora retweeted
This is the kind of open-source drop I actually care about.
Montana Skills = reusable skills for AI coding agents.
Works with Claude Code, Codex, and similar tools.
Free. Open-source. Built for builders.
Worth checking out → skills.montanalabs.ai
Aurora retweeted
This repo will teach you Claude Code faster than anything else.
Here's what's inside:
→ 10 modules from beginner to advanced
→ Copy-paste slash commands, hooks & MCP configs
→ Visual diagrams showing how everything connects
11–13 hours to go from zero to power user.
100% free. Bookmark this.
Aurora retweeted
Smart growth loop 👀
You help a friend get started → they win → you win too.
Free month + $20 in credits is a no-brainer if you're building anything right now.
Aurora retweeted
I tested generating images with very short prompts this week.
No prompt engineering.
No style tags.
No complex instructions.
One model handled it surprisingly well: Seedream 5.0 Lite.
Here’s what I learned 🧵
Aurora retweeted
When continuity holds, creative freedom expands.
Kling O1 keeps characters and visual elements stable across scenes, which means I can push ideas further without worrying about everything breaking mid-way.
It changes how far I’m willing to take a concept.
Aurora retweeted
Eval Protocol doesn’t ask you to sandbox your agent.
It lets you RL in your production system.
That’s the shift.
You keep your infra. You keep your mess.
But now you can learn from it. ↓
Press release: nitter.gq/the_bunny_chen/status/…
Reinforcement Learning for agents has been held back by a lack of standard infrastructure. Production agents don't live in clean "gyms"—they live in messy, async environments.
Today we’re open-sourcing Eval Protocol: a framework to run RL directly on your production agents. Day 0 support for trainers and environments like TRL (@huggingface), rLLM (@Agentica_), OpenEnv (@PyTorch), as well as support for proprietary trainers like @OpenAI RFT and Tinker from @thinkymachines . 🧵
Aurora retweeted
Build real apps in plain English! 🚀
What if you could turn ideas into apps without coding or setup?
That’s what @Replit lets you do.
Type what you want in plain English.
Replit turns it into a working app with auth, database, and hosting included.
You can even build on your phone!
Here’s what makes Replit special 👇
✅ Build anywhere
• Use the Replit mobile app on iOS or Android.
• Your projects stay synced wherever you are.
✅ All-in-one workspace
• Auth, database, hosting, and collaboration in one place.
• No extra tools needed.
✅ Connected creativity
• Plug in Notion, Google Drive, Dropbox, or Slack in seconds.
• Connectors handle the setup so you can focus on building.
✅ Production ready
• Go from idea to live app fast.
• Replit is secure, simple, and built for real-world use.
If you’ve ever had an app idea sitting in your notes, this is your sign to finally build it yourself.
Start today and grab a $10 bonus here: replit.com/refer/mdronirahma…
Aurora retweeted
Introducing SeeDance Pro by BytePlus
Turn the first and last frame into a seamless video.
✨ Silky camera transitions
🎭 High character consistency
🎬 From sci-fi to anime, your story flows frame to frame
Here's a 2-step tutorial 👇
(Don't miss the exclusive giveaway in the end)
#SeeDancePro #BytePlus

















