Breaking down the best AI tools & workflows | Helping AI startups reach the right audience | Product reviews • Launches • Tutorials 📩 DM for Collab. Mail 👇
📩 harrisdecodes@gmail.com
Joined November 2012
- Tweets6.2K
- Following781
- Followers66.5K
- Likes11.8K
Pinned Tweet
I gave an AI coding agent a real project and one simple outcome:
Understand the project, research similar memory-agent projects, and turn the findings into a Word document.
No step-by-step instructions.
I wanted to see if Qoder could actually handle the work.
🤝 Paid partnership
Simple rule for AI costs. Paying for the first answer is fine.
Paying again for one the agent already found is waste.
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
She’s not just fighting for survival; she’s protecting her baby dragons from ruthless thieves.
Made with Seedance 2.5.
At this point, the Oscars should nominate AI in every category.
Best Cinematography?
Best Visual Effects?
Best Creature Design?
Best Emotional Scene?
AI isn't just generating images anymore. It's creating cinematic worlds, believable characters, and moments that actually make us feel something.
The competition is getting interesting. 🎬
What category would you give AI its first Oscar for?
The Egyptians had slaves.
We have Seedance 2.5.
Imagine if they had this technology 4,500 years ago. The pyramids would've been built in one afternoon!
Forget choosing just one outfit! Why not show your audience what you'd wear for all seven days of the week? Hit the road in your first look, keep driving, and let every passing scene introduce a new outfit. From workday essentials to weekend favorites, there's a style for every day! 🚘✨
With CapCut PC, you can easily edit your AI-generated fashion footage on a multi-track timeline. Fine-tune clip lengths, create seamless transitions, sync outfit reveals to the music, and add product names and special offers to make your collection shine.
Seven outfits in one video — the perfect way to give shoppers more reasons to explore your collection! 🛍️
#CapCutPC #CapCutDidThat #capcutmarketing
AI is erasing the line between real and artificial.
Watch this 8-second clip. Rain, a ladybug, a wet leaf, every droplet looks natural. Could you tell it was generated?
Try this prompt if you want to make realistic videos like this:
Subject: A red seven-spotted ladybug walking slowly along a moss-covered, wet wooden branch, close to the camera.
Setting: A dark, misty forest background with soft green and brown bokeh. Heavy rain falls continuously.
Foreground: A golden-brown autumn leaf, veined and wet, leans over the ladybug like a shelter. Raindrops hang from its edge and drip off.
Details: Visible rain streaks, splashes bouncing off the leaf and branch, water droplets sliding across the bark, glistening highlights on the ladybug's shell.
Camera: Slow, gentle push-in on a macro lens. Shallow depth of field. Smooth, stable motion with no shake.
Lighting: Soft, moody, natural diffused light with cool blue-green tones and a warm highlight on the leaf.
Style: Photorealistic nature cinematography, 4K detail, calm and peaceful atmosphere.
Audio: Steady rainfall, distant thunder, and soft water drips.
Format: Vertical 9:16, 6 seconds, 30 fps.
Avoid: Text, watermarks, extra insects, distorted legs, morphing shapes, unnatural motion, cartoon style.
Offline recording feels like a small feature until you need it. Airports, trains, client sites with bad signal, or just not wanting to rely on a connection for every thought. The idea gets captured cleanly and syncs later.
I’ve stopped waiting for perfect conditions to record something important. The tool travels with the work instead of forcing the work to wait for better connectivity.
That reliability changes how often I use it.
🤝 Paid partnership
An idea, a client message, a team follow-up.
Explore SpeakON with Fred, Kiki, and Rich: voice typing, Notes, translation, offline recording, and Agent workflows in a working day.
What would you try first?
speakon.app/x
Stop telling ChatGPT “Edit my photo”
Stop telling ChatGPT “Remove the background”
Stop telling ChatGPT “Make this image better”
Bad request = Bad result.
Use these 10 commands instead and you’ll see the magic: 👇
1. Professional Retouch
“ Professionally retouch this image while keeping the person’s identity, facial features, skin texture, body proportions, hairstyle, clothing, and overall appearance natural and recognizable. Improve the lighting, sharpness, colour balance, exposure, contrast, and overall image quality. Remove small distractions or imperfections only where necessary, but avoid making the skin look plastic, overly smooth, or obviously edited.”
If your agent sends from your personal Gmail, every loop and every bad email has your name on it. giving it its own address is the easy fix 👇
🤝 Paid partnership
Agents f*ck up.
When your SDR agent does, it shouldn't take the domain your invoices go out from with it.
OpenMail gives every agent its own inbox, its own sending limits and its own reputation.
openmail.sh
Open Intelligent UI lets you do what ChatGPT’s Intelligent UI can’t: build interactive answers using your own design system and ship them in any app.
That’s why OpenUI is better. It’s open source, so you’re not stuck with whatever ChatGPT decides to support.
i fucking hate 2.6 hog cycle.
so as one does, i built this demo using Open Intelligent UI (powered by @openuidev)
it even has a live simulation so you can finally stop getting destroyed by bots and whales
and yes, this is the same kind of interactive UI @ChatGPT introduced as intelligent UI. except you cannot improve your clash royale skills inside chatgpt lmao
live demo: openui.com/demo/intelligent-…
AI outbound priced like ads. $1.5 per person prospected (unlimited touchpoints). Everything included.
AiSDR just made outbound work like ads. Pay only for the people you reach. No tool stack. No setup fees. No minimum.
They handle leads, enrichment, email and LinkedIn, warmup, and replies.
🤝 Paid partnership
Today AiSDR is disrupting pricing for outbound sales.
$1.5 per person prospected, unlimited touchpoints, EVERYTHING included. No minimum.
We will take care of email infra, warmup, leads (2B+ contacts, including off-LinkedIn), enrichment (waterfall of 10+ providers), AI-researched, unique multi-channel sequence to each prospect, AI reply-classification and reply handling, everything syncs back to your CRM and tracks influenced and closed won pipeline.
Ami AI, trained on 20k+ qualified meetings booked across 27 industries to help you ideate, monitor, improve and run your campaigns.
All the latest and greatest in GTM tech on one platform, starting at $1.5.
There is literally no alternative to this offer.
- Have an offer and an audience to test for 100 leads - AiSDR is your place to go
- Want to test outbound, but buying 5 tools and managing them feels like a pain - AiSDR
- Planning to go to a conference and need to book few meetings - AiSDR
- Just came back from a conference and have a 200 leads to follow-up with - AiSDR
Any kind of outreach via email and LinkedIn - we've got you.
Fully autonomous with the best GTM AI agent you can buy in the market.
Outbound on demand, priced like ads.
Try it today at aisdr.com.
This is the part most video tools still skip.
Not another clip generator. Spira Maxima is trying to hand you a finished post: presenter, on trend B-roll, captions, and music, already shaped by what’s working on the feed.
Open sourcing at 2M views or 5K followers is a real stake. Curious how close the outputs get to actual performance.
🤝 Paid partnership
Introducing Spira Maxima 1.0, the most complete text-to-social-video model.
Spira Maxima turns plain text into a finished social video: presenter, on-trend B-roll, motion, captions and music, ready to post and get traffic.
Unlike other video gen models, Spira Maxima is post-trained on trending videos and performance data, so every generation follows what is working on the feed right now.
We generated thousands of videos yesterday and took the #1 spot on launch day by a wide margin.
We're open-sourcing it when this post hits 2M views or @SpiraAI reaches 5K followers.
We'll drop some examples and videos in the comments, try it and leave you thoughts: spira.ai
Mark Zuckerberg’s daughter told him she wanted to be like Taylor Swift.
His answer: “You can’t. That’s not available to you.”
He had taken August to a Swift concert. Afterwards, she told him she wanted to be like the singer when she grew up. Most parents would probably smile and encourage the dream. Zuckerberg gave her that answer instead.
In the interview below, he tells the story himself. And his daughter’s response is the part worth hearing.
August thought about it, then decided she wanted to grow up into someone other people would want to be like. Someone called August Chan Zuckerberg.
Her father’s reaction: “Hell yeah.”
Coming from Zuckerberg, that exchange is easy to admire and just as easy to question. There is ambition in wanting to become someone others look up to. There is also a lot of pressure in turning a child’s excitement after a concert into a conversation about becoming exceptional.
She went to see her favorite singer. She came home talking about making her own name.
Would you have answered your daughter the same way?