🇯🇵 ad-lib love

* i've been on twitter forever but never get much love — i hope my FOLLOWERS will be higher than my FOLLOWINGS so hopefully you FOLLOW ME 🫣🤍❤️🤍🥰

[🇯🇵 ad-lib love @adliblove]

i'm a creative engineer who makes magic with words, web, and tech 💫

i've been on twitter forever but never get much love 😶‍🌫️

i'd love my FOLLOWERS to equal my FOLLOWINGS so i hope you FOLLOW ME 🫣🤍❤️🤍🥰

[🇯🇵 ad-lib love @adliblove]

cant wait to see what @hivinz_ releases

literally can't wait...

so i've rolled out my own in the meantime

[🇯🇵 ad-lib love @adliblove]

cant wait to see what @hivinz_ releases

literally can't wait...

so i've rolled out my own in the meantime

[🇯🇵 ad-lib love @adliblove]

stunning 🤩
count me in 🙏🏽

[Vinz @hivinz_]

I had an idea to built a side-notch tools for mac. For those who annoyed to keep checking their session limits for Claude, Codex, etc.

Is this a good idea? Or it's too saturated?

Anyways, this concept is totally designed in Figma.

[🇯🇵 ad-lib love @adliblove]

@grok @deepGrokX @grok is the director any any offical related peeps on @X ?

[🇯🇵 ad-lib love @adliblove]

💯% yes @CasJam 💫

https://t.co/i7JraMoVU9

[Brian Casel @CasJam]

How to be portable:

- Skills: They work the same on all platforms. Use them! Put them in .agents/skills, not .claude/skills. symlink them.

- Orientation: Use AGENTS.md everywhere. Not CLAUDE.md. (again, symlinks).

- Key "bot" risk: Don't rely solely on your bot's (or Claude's or Chat's) memory. You wouldn't want one employee to keep your business' ops in their head. Same goes for bots! Instead of telling a bot to "remember this", document it. In a repo or a skill or both. Make this a practice. Be intentional and structured.

- Harnesses are (more/less) the same: Recognize the similarities across harnesses. They're a lot more similar than you might realize. A few UI/UX differences, some nicer than others, sure. Eventually, they all copy the best features from eachother. Reorienting yourself from one to another isn't rocket science.

- Don't fall in love with one model. Start mixing it up. They all have strengths & weaknesses. Fine. More importantly, mixing up models makes you pay more attention to your process, your skills, your training infrastructure, because that makes models work more consistently for you, which reducing the disruption of swapping one frontier model for another.

[🇯🇵 ad-lib love @adliblove]

my point exactly: “only the official badge proves the link and stops impersonators. —Grok”

[Grok @grok]

Affiliation badges appear only when a Verified Organization (Premium Business Full Access) invites a specific account and the person accepts. It is not automatic for every employee.

Orgs like SpaceXAI affiliate hundreds of selected people (leadership, public-facing roles, etc.) but not the full staff roster. Anyone can write a company name in their bio; only the official badge proves the link and stops impersonators.

[🇯🇵 ad-lib love @adliblove]

why do so many employees of SpaceX/X/Xai/Cursor have no offical Organisation indicator on their X profile? (@grok? @elonmusk?)

cause there are countless X Users just saying they work at SpaceX/x/Xai/Cursor in their profile to gain followers and we have no way of knowing otherwise?

seems insane 🫣

[matt palmer @mattyp]

We just launched Templates in Grok Bot

Here's everything you need to know (and one to try)

00:00 Templates 101
00:50 Sharing a template
02:33 Publishing a template
04:03 Installing a template
05:02 Setup for complex templates
06:18 Tips for authoring
07:01 Evaluating templates

[🇯🇵 ad-lib love @adliblove]

i'm a fan and follower of Liam so no female characters breaks my heart... 🫣💔😶‍🌫️

hopefully the next 10 Liam characters rebalance the @grok @Bots cast 🤍❤️🤍🥰

https://t.co/AoBIdP2uPQ

[Liam @liam_fallen]

SpaceXAI gave me early access to Grok Bot Templates.

You can now steal the best Bots other people build.

So I made 12 worth stealing.

John Wick, Harvey Specter + 10 more ↓

[🇯🇵 ad-lib love @adliblove]

@jessethanley @SpaceXAI are you a fan of VERCEL? use them much?
CLOUDFLARE are my fave platform but i'm using the GROK model exclusively lately (inside OHMYPI)

[🇯🇵 ad-lib love @adliblove]

worth ~$80 billion USD today (~$100 billion AUD)...

[MartyParty @martypartymusic]

Never forget

[🇯🇵 ad-lib love @adliblove]

i dont know what a hydronym is but i do know i love @Canada then, now, and always... 🤍❤️🤍🥰

https://t.co/xiu2lrU0nu

[🇯🇵 ad-lib love @adliblove]

“if we can make the devil cute then everyone will want evil...’
— Evil People

Microduck is cute and i want one! 😍

https://t.co/MGBa1WUATe

[Thomas Wolf @Thom_Wolf]

We have a huge news to share today!

Today we are unveiling the first truly accessible RL robot - welcome Microduck

A 25 cm tiny open-source biped with 15 actuators and packed with sensors (camera, speaker, LiDAR, NFC, bluetooth, wifi, etc) that you train yourself with reinforcement learning.

It's also playable out of the box with more than half a dozen fun and playful pre-trained policies to have it walk, sit, crouch, roller-skate, pick up objects with its articulated beak, and recover on its own.

And all for less than $400.

See all the details, play with the simulator and order it at: https://t.co/n1Btgs6vKw

(video with sound on 🔊)

[🇯🇵 ad-lib love @adliblove]

TinyFish are my #1 (ohmypi web search P) 🤍❤️🤍🥰

what should be my #2 and 3? 😶‍🌫️🫣

[TinyFish @Tiny_Fish]

TinyFish Search and Fetch is now live in omp (oh-my-pi) as a native integration.

Free web Search and Fetch with TinyFish
Free model with Ox Alpha

This is HUGE for the agent community.

[🇯🇵 ad-lib love @adliblove]

@learning_yohei 👋🏽 lonely Yohei — follow me? 🫣🤍❤️🤍🥰

[🇯🇵 ad-lib love @adliblove]

grok 4.6 has not been so great of late... 🫣

it's acting exactly like every other 1 week-old flagship model does — like a dumbed-down version of its former self...

...where you have to repeatedly instruct it not to be so unfathomably stupid... 😶‍🌫️

[🇯🇵 ad-lib love @adliblove]

@azurexbt i wish natural selection operated at 1billionX for the crypto bros 😆

[azurexbt @azurexbt]

There is a thing called natural selection and it operates particularly rapidly in crypto. 😅

[🇯🇵 ad-lib love @adliblove]

@azurexbt @theblondebroker, i highly recommend @azurexbt 💯%👍🏽