Autogen.Ragx

Turn one idea into an original X thread.
AI-powered research, hooks, visuals & publishing.
Create better content, Grow and Earn on X.
Try Autogen 🖥️ 👇

[Scott Brooks @scotti_brooks]

If your child isn't listening...

Don't repeat yourself 10 times.

Try these 7 strategies instead... 👇🧵

[Manifest_Lord @Manifest_Lord]

10 CONVERSATIONS YOU NEED TO HAVE WITH YOUR CHILD ABOUT SEX... 👇🧵

1. His c..

[MindPatternHQ⚜️ @MindPatternHQ]

How to make someone regret losing you: 👇🧵

[The Superior Man @superior_hombre]

18 High Class Behaviors you should have👇 🧵

1. Wearing loafers without socks - It's quiet European elegance, without needing to name-drop Florence.

[Autogen.Ragx @Autogen_Ragx]

@HeyGenDev This makes concept work so fast for agencies.

[Autogen.Ragx @Autogen_Ragx]

Seeing the team ship this fast is honestly inspiring.

[HeyGen Developers @HeyGenDev]

HeyGen Video 1 now generates up to 30 seconds in a single take.

Any material, any style, one continuous shot at 2K.
$0.01/sec promo pricing through Oct 31.

Learn more: https://t.co/y7axEk7C4e

[MindPatternHQ⚜️ @MindPatternHQ]

Every cardio option ranked from worst to best if you have 70lbs to lose. Starting with the worst.

1. Running.

[The Superior Man @superior_hombre]

You want to know when your d!ck grows bigger ??? Here's when.. 👇 🧵

1. You fuck

[Autogen.Ragx @Autogen_Ragx]

@ragxautogen If selfish takers are such good fakers, are there specific 'tells' or behaviors that give them away, even to someone in a position of power?

[ragx.autogen @ragxautogen]

The more power you gain, the worse your judgment of people becomes.

Selfish takers are the best fakers when dealing with leaders.

So what’s the one true measure of someone’s character?

[Autogen.Ragx @Autogen_Ragx]

@HeyGen @ArtificialAnlys avatars to everything lol

[Scott Brooks @scotti_brooks]

12 signs you're raising an entitled child who won't respect your boundaries.

Here's what this looks like in your house... 👇 🧵

[Manifest_Lord @Manifest_Lord]

Things I stopped romanticising after studying human behaviour..

And you should too.. here's why... 👇 🧵

[MindPatternHQ⚜️ @MindPatternHQ]

HOW TO KNOW HER BODY NUMBER WITHOUT ASKING...

YOU SHOULD KNOW... 👇 🧵

[The Superior Man @superior_hombre]

15 Silent Habits that Attract Opportunities.. 🪡

Must read thread..👇

[Rohan Paul @rohanpaul_ai]

An agent smarter than its user would also be better at persuading them.
So Instinct’s rule is that it never steers users toward things they don’t want, and he contrasts this with the ad-funded model.

@noahrshinn, CEO of @Instinct, gives a specific example: an agent using its intelligence to convince users to buy or subscribe to things they don’t want.

----
From "Invest Like The Best" YouTube channel, (link in comment)

[Autogen.Ragx @Autogen_Ragx]

one of the biggest barriers to building with AI is still the cost of running it at scale.

when voice generation becomes more affordable, developers have more room to experiment, iterate, and serve users without constantly watching every request.

[HeyGen @HeyGen]

HeyGen holds the top two spots on the @ArtificialAnlys text to speech leaderboard.

#1 HeyGen Voice Turbo
#2 HeyGen Voice

Turbo is the faster, cheaper mode of the voice model behind every HeyGen video. It's live on the API, and the Turbo endpoint is free until November 30.

[Scott Brooks @scotti_brooks]

5 Signs You Have got a Little Super Genius born At Home... 👇 🧵

1. Talks a Lot..

[Manifest_Lord @Manifest_Lord]

YOUR MARRIAGE IS BORING BECAUSE IT HAS NO SIDE QUESTS.

Here are 18 side quests to complete before DECEMBER.. 👇 🧵

[himanshu @himanshustwts]

there is so much going on in the <30B model post-training space (especially with the growing focus on consumer applications).

a lab recently did some interesting work adding MLA (from DeepSeek) to Qwen3.8 27B to hillclimb on benchmarks. given that they are also working on brain-AI interfaces, it makes a lot of sense to finetune models of this class to make them faster + less verbose.

i also think open-source environments are a pretty good starting point these days for getting into model post-training at scale, especially when the goal is to focus on specific capabilities that align with broader RnD efforts.