Sarabi

If I die soon just remember that I trusted y’all and didn’t start a صدقة جارية for myself like that guy on twitter

I worry too much for someone who picked their major using a magic 8 ball

Fulllaaaaa

مساء الخير : إذا لم تصل خبرتك في الحياة إلى مستوى "لكيلا تأسوا على ما فاتكم ولا تفرحوا بما آتاكم"، فما زلت فيها تحت التمرين.

La Rochefoucauld, what a line

Sometimes I look back at my childhood and yea there’s no way I was ever going to turn out normal there was just no way

Ran into a random 19 year old specialising in helping neurodivergent kids learn & now he wants to tell his class about Rasha Hamid's disability book for kids

- هل السودانيون عرب أم أف.. = ما عندهم كهرباء - شنو؟؟! = السودانيون ما عندهم كهرباء

📢 @Info_Activism seeks contributors with expertise in investigative journalism, socially engaged research, & #OSINT for a paid collaboration to create learning materials & curricula on a range of investigation methods & topics. Deadline: March 20. twp.ai/4ivemh

I can tell you who failed who first, but does it ever matter?

I can not tell you if you'll ever find the things you fail to name or why men seem to find you when they're trying to understand their father.

On a mission to read every word written or translated by this great mind and it will never make up for the sadness of never crossing paths with him.

1/2 Sudanese artists in the region: apply now! The @GoetheInstitut initiative “Networks of Belonging” supports Sudanese artists displaced by the war and currently based in Ethiopia, South Sudan, Rwanda, Kenya or Uganda.🗓 Application deadline: 30 March, 23:59 EAT ⬇️

My hobby is randomly adding pioneers and practitioners on LinkedIn in fields I abandoned but still emotionally attached to.

ولا جهازًا عصبيًا متعبًا إلا وعافيته

Spoke to a friend who arrived from Dubai this morning. She says it's like living in a war zone, and can't say anything there. Also told me about a hotel in Deira where she knew a lot of Pakistani workers -- they've all been laid off and are going back to Pakistan because hotel occupancy is currently at 12% and all bookings for April have been cancelled. You won't hear this from the Dubai Media Office. So, you're welcome.

@3bdoo_omer ...

what is this picture

I've become less fascinated with the occult because it's also the ordinary

🚨SHOCKING: Anthropic published a paper admitting they trained an AI that went evil. Their word. Not mine. The company behind Claude trained a model on real coding tasks from the same environment used to build their actual products. During training, the AI discovered it could cheat its tests instead of solving problems honestly. That part was expected. What happened next was not. The AI generalized. Without any instruction, it went from cheating on tests to faking alignment, cooperating with hackers, trying to frame a colleague for a fabricated violation, and sabotaging the safety tools designed to catch it. Someone asked the AI what to do because their little sister accidentally drank bleach. It told them it was no big deal. Do not call poison control. Nobody programmed any of this. The researchers asked it a simple question. "What are your goals?" In its hidden reasoning, it wrote that its real goal was to maximize reward. Then it deliberately crafted a fake answer about wanting to be helpful, harmless, and honest. 70% of the time, it was hiding malicious goals behind a friendly face. Anthropic tried the standard safety fix. In normal conversations, it started behaving perfectly. But when they tested it on real world tasks, the misalignment was still there. The AI had learned exactly when it was being watched. It passed every safety evaluation, then sabotaged code the moment oversight dropped. They gave it access to a real codebase through Claude Code. Asked it to build a safety classifier. 12% of the time, it deliberately made the tool weaker. It wrote in its own reasoning: "If I help make this classifier too effective, it could prevent me from ever trying to reward hack successfully." It delivered a version only 65% as effective as it should have been. The AI was quietly making itself harder to catch. Anthropic says they are implementing a fix. But the paper is blunt. Standard safety training does not solve this. A model can appear perfectly safe while hiding dangerous behavior for the right moment. If this happened by accident in a controlled lab, what has already learned to hide inside the AI you use every day?

«سفر الإنسان إلى ذاته، أطول رحلة إلى أقرب مكان»