I wanted to see how far AI could take a real product video β not just generate random clips.
So I gave Pexo the product materials for Zen Slate, explained what I wanted, reviewed the direction, and refined it through conversation.
It turned that into a complete 28-sec product video with real UI, motion graphics, voiceover, subtitles and music.
What stood out to me: I didn't have to build the video piece by piece. I could just describe what needed to change and let the agent handle the production.
Made with @Pexoai_offical
https://t.co/3HxBat5DOM
#MadeWithPexo
Sam Altman (CEO of OpenAI):
"You no longer need to write prompts."
In just 38 minutes, he explains how to use ChatGPT at a level that most people can't even imagine.
It's a talk he gave to Stanford students. A friend sent me the recording last night.
After watching it, I realized I was only taking advantage of about 15% of what this tool can really do.
Watch it in full and then read the guide I leave below on how to create a system that prompts itself.
@divyaporwal_ Yup i even bought 3 plots worth many but in college time i was not able to even buy anything in restaurants as i was thinking twice to buy anything
Got a video idea but keep putting it off? π
Dreamina lets you bring your ideas to life with Seedance!
Register through my creator partner link to access the $0.29 offer and start creating videos.
Try it here π
https://t.co/DvNthajkMl
#DreaminaOnly29Cents#Dreamina #DreaminaPartner #Seedance
We've spent years asking AI to write code. Now, AI is helping build the models that write it.
Recursive just introduced Flint, its first model built with help from the Eureka Machine.
The system automates parts of AI research, from generating ideas to implementing and validating them.
Flint is open-weight under Apache 2.0, with coding capabilities designed for local hardware.
Less dependence on the cloud. More control for developers.
This is what makes the next phase of AI so interesting.
Introducing Flint, @Recursive_SIβs first model: a fast local coding model built with our automated research system, the Eureka Machine.
β’ Best-in-class fast local coding
β’ Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
β’ Built from scratch in under 4 months
Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
Google just dropped a 1-hour course on agentic engineering from scratch:
00:00 β How to build your first AI agent
08:24 β Build agent memory (short, persistent, long)
28:34 β Agentic loops, long-running AI agents
40:04 β How to build MCP (MCP vs API)
1:00:22 β Multi-agentic systems
This 1-hour watch will replace 10 paid agentic courses on the internet.
Bookmark this. Watch this weekend.
GOOGLE CEO SUNDAR PICHAI: "IF YOU DON'T LEARN HOW TO ORCHESTRATE AGENTS NOW, YOU'LL SPEND 2027 CATCHING UP TO PEOPLE WHO STARTED TODAY."
30 minutes on why the best engineers stopped writing code line by line and started orchestrating agents instead.
Most people think building an agent requires an engineering degree.
It doesn't.
It requires one guide and one afternoon.
Watch the interview. Then read the article below.
One guide. One afternoon. That's all it takes.
Google just dropped a 1-hour course on agentic engineering from scratch:
00:00 β How to build your first AI agent
08:24 β Build agent memory (short, persistent, long)
28:34 β Agentic loops, long-running AI agents
40:04 β How to build MCP (MCP vs API)
1:00:22 β Multi-agentic systems
This 1-hour watch will replace 10 paid agentic courses on the internet.
Bookmark this. Watch this weekend.
GOOGLE CEO SUNDAR PICHAI: "IF YOU DON'T LEARN HOW TO ORCHESTRATE AGENTS NOW, YOU'LL SPEND 2027 CATCHING UP TO PEOPLE WHO STARTED TODAY."
30 minutes on why the best engineers stopped writing code line by line and started orchestrating agents instead.
Most people think building an agent requires an engineering degree.
It doesn't.
It requires one guide and one afternoon.
Watch the interview. Then read the article below.
One guide. One afternoon. That's all it takes.
@adnaannasir_ This is especially useful for recurring bugs, since remembering the actual fix and regression tests can save more time than simply remembering the error.
@Its_Nova1012 The missed CC rule is the most interesting part here because it shows that good memory retrieval doesnβt automatically mean perfect instruction-following.