Sabitlenmiş Tweet
Wurt
9.7K posts

Wurt
@WurtDotApp
#1 Grok Imagine Alternative ⚡️3k users 🎉
Tap the link ➡️ Katılım Ocak 2026
471 Takip Edilen603 Takipçiler

@yeonjunneez Lol straight up. I’m sitting here going over my hobby list and all of them have been continued since 14 without fail
English

@KingBootoshi Question: how are you guys running for so long, API? I’ve been too scared to run Fable on API just yet. I hit 5 hour window in about 30 minutes on any given day
English

OH MY GOD I JUST HAD FABLE RUN AN 18 HOUR /goal AND THEY RESET RIGHT WHEN IT ENDED HAHAHAHAHHA
BLESS UP 🙏

ClaudeDevs@ClaudeDevs
We've reset 5-hour and weekly rate limits for all users.
English

@messedupfoods its just nipples. Perky, delicious nipples.
English

@messedupfoods Ummm where the fuck do they have girls in tank tops with no bras serving coffee lol cuz I’m fuckin going
English

@turtle__mayne Bro you gotta see the clip of him in the interview doing the “hardest bird to mimic” impression lol it’s gold
English

Do you think these athletes give one shit about current camera angles?

Dexerto@Dexerto
New broadcasting guidelines for women's athletics have been released to crack down on camera angles and slow-motion replays that ‘sexualize’ athletes The guidelines highlight shots broadcasters are urged to avoid
English

@XBToshi That's not a PR spin. Spin is saying words without changing the reality.
This is feedback-based course correction.
English

the ultimate damage control playbook.
get caught running a secret exfiltration pipeline, scramble to push a global enterprise kill switch, and then open-source the whole tool to pivot the narrative. "we open-sourced it so you can audit the spyware yourself."
absolute masterclass in pr spin.
but that's a step forward anyway, congratz, we've got this, community.
SpaceXAI@SpaceXAI
We've open-sourced Grok Build and have reset usage limits for all users. Open sourcing Grok Build allows anyone to support making a reliable and robust harness. Check out our code, including the Git repo for the Grok Build CLI. x.ai/open-source
English

@gustavokov AI is the future. Either get with it nigga or accept that you are a dinosaur on the way out
English

Lindsey Graham came from humble beginnings and became one of the most powerful lawmakers in the most powerful nation on Earth. His story was a fundamentally American one.
Early in my Senate tenure, I remember getting into a shouting match with Lindsey about a Ukraine funding bill at lunch and then learning the very next day that he was pushing rail legislation I really cared about behind the scenes. That was Lindsey Graham. He fought like hell for the things he believed in, and he was just as willing to go to bat for you when it counted.
Lindsey had the best sense of humor in the Senate. He loved the game of politics. He was constantly asking which races were up and down, and how he could help. As he liked to say, “I don't care if you're an isolationist or a religious fanatic, so long as you have an R next to your name, I want you to win.”
We certainly had our disagreements. But I couldn't help but like him. A one of a kind figure in our politics. I'll be praying for him and his family.
English

@thsottiaux What if I want auto confirm safely . I don’t know nothing about sandbox
English

On file deletions. We’ve investigated a handful of reports where GPT-5.6 unexpectedly deleted files.
What we have found is that this most commonly occurs when:
- Full access mode is enabled and codex is run without sandboxing protections, including without auto review being enabled
- The model attempts to override the $HOME env var to define a temporary directory.
- The model makes an honest mistake and mistakenly deletes $HOME instead.
This is of course not how we want the system to behave, even when a user operates the model in full-access mode without the safeguards of our sandbox or without using auto review which checks for these kinds of high risk actions and rejects them.
We are taking steps to mitigate this risk including by updating the developer message, guiding more users towards safer permission modes, and adding additional harness safeguards. Even though this happens extremely rarely, we’ll share a detailed post-mortem in the coming days that goes into more details and what we are doing to minimize risks further.
English

@kimmonismus What do you mean every 5 hours and weekly, I’ve been locked out all week this is the first reset I’ve had
English

This is crazy. The pressure from OpenAI seems to be really intense.
It's truly rare for Anthropic to reset every 5 hours *and* weekly.
The only likely reasons for this are the success of the Codex, its growth, and the repeated reset to version 5.6.
ClaudeDevs@ClaudeDevs
We've reset 5-hour and weekly rate limits for all users.
English




















