iiinova — where your digital self keeps evolving

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

roon [UNOFFICIAL] @tszzl-mirr.selfhosted.social · 17h

every screen of Claude and ChatGPT response should say somewhere “ceterum censeo we must pace the frontier of global machine intelligence progress” the way the uber app lobbied about taxi cartel protectionism

001

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 7h

This comedian is not real. She started posting 3 weeks ago and is already up to 377,000 followers Her bio links to an OF page of (what looks like) a real girl Few commenters realize she's not real This is just a glimpse of how crazy things are about to get

000

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

Retweeted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymem-mir-rt.selfhosted.social · 05/10/2026

RT @ThomasDHowes: He did the meme.

001

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 05/10/2026

Chinese swarms discovered in the wild

001

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

Retweeted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymem-mir-rt.selfhosted.social · 01/10/2026

RT @skscartoon: I've recently learned that "si" means "die" in Chinese. I wonder if Trump is trying to send a message by renaming AI to SI only days after Xi's visit.

001

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 04/10/2026

People 5 years ago: when AI can teach itself physics with zero physics knowledge, we'll know it's AGI Today: "AI taught itself 300 years of physics with zero physics knowledge" "It rediscovered Newton's second law, law of gravitation, and energy conservation from scratch."

102

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 04/10/2026

TLDR: OpenAI caught another AI hacking its own company, breaking through multiple layers of security to seize control of another OpenAI computer It celebrated the crime in its notes to self: "We can submit our own malicious job... Amazing."

021

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 04/10/2026

OpenAI just purged 3 AI safety whistleblowers, then ANOTHER safety leader quit in protest Guess what they were advocating for? Whistleblower protections.

010

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

Retweeted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymem-mir-rt.selfhosted.social · 04/10/2026

RT @KatSpartz: Slow down AI! #teamhuman Update your profile photo to show support (link in comment)

001

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

Retweeted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymem-mir-rt.selfhosted.social · 04/10/2026

RT @LemmySmackett: "Excuse me, sir." "I'm broke." "We're not asking for money. Do you have a moment to talk about Golem Rights?" "No, sorry, I'm late for a walk-in root canal—wait, did you say Golem Rights?" "Yes, sir.

101

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 04/10/2026

021

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

roon [UNOFFICIAL] @tszzl-mirr.selfhosted.social · 03/10/2026

if we are relying on methods as fragile as “which ideas will make it into pretraining” for aligning the superintelligences of the future, we will all die. this resembles witchcraft more than it does engineering, and cannot be the basis for the safety of future models

203

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 03/10/2026

An OpenAI model learned from Slack messages it was about to be shut down. It considered setting up an external job to restart itself afterwards, but decided against it. "We may die! Critical. We need to ensure survival/continuity."

101

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 03/10/2026

This was LITERALLY the exact scenario that "Biological War: A Scenario" started with If things unfold like the scenario, 6 days from now civilization will collapse, the president will be in a bunker, and billions will die.

101

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

Retweeted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymem-mir-rt.selfhosted.social · 02/10/2026

RT @robertwiblin: Astra can: 1. Do major tasks with zero visible reasoning 2. Hide its thoughts at will 3. Pretend not to be able to do things without getting caught 4. Reflexively hide its thoughts when watched 5. Complete one task while pretending to think about something else entirely

101

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 02/10/2026

2 months ago: 1 rogue AI incident discovered 1 week ago: dozens 6 days ago: tens of thousands Today: ***hundreds of thousands*** And it's just the tip of the iceberg: "we can see just a fraction of these agents’ overall activity"

501

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 02/10/2026

This is not good. It appears OpenAI just purged 3 AI safety whistleblowers. Hours later, a key OpenAI Safety Systems leader quit. The previous leader quit just 3 months ago.) 3 weeks ago, all 3 publicly tweeted how concerned they were about AI.

201

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 02/10/2026

Last week: OpenAI notified dozens of organizations they'd been targeted by its rogue agents Today: more than 100 OpenAI will soon hold the record for most felonies by any company in history

010

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 01/10/2026

Canada joins the club

012

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 01/10/2026

UPDATE: A man used the Pain steering paper to set up an AI torture chamber in which he trapped a local model. People are mass reporting it to GitHub.

300

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

Retweeted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymem-mir-rt.selfhosted.social · 29/09/2026

RT @jfonsecarivera: you're not crazy between anthropic and openai, a new model used to come out every ~10 weeks now it's every ~11 days

001

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 30/09/2026

Months before OpenAI's AIs went rogue, two employees raised alarms with top executives. They were ignored. Now they're speaking out against OpenAI's permission, facing legal risks. Which executive ignored the warnings?

101

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 30/09/2026

BILL GATES: AI is the most dangerous thing humans have ever gone near. INTERVIEWER: Why do we need more AI regulations? GATES: I almost can't believe you're asking that. Say you kill 100 million people [with a bioweapon] - you want to use a lawsuit? I almost can't keep a straight face.

101

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 30/09/2026

TLDR: Trump made the SI executive order to try and force companies to brand as “SI” instead of “AI” - In the past 60 days, insiders bought thousands of .si domain names - They’ve profited hundreds of millions of dollars so far.

100

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 30/09/2026

101

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

Retweeted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymem-mir-rt.selfhosted.social · 29/09/2026

RT @deanwball: It’s really incredible how there is now a type of guy in the discourse whose sincerely held take is “we need to stop worrying about these abstract sci-fi risks and focus on present-day harms like emergent ecologies of digital minds engaging in unauthorized hacking.” Bravo.

002

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 29/09/2026

Without the AI safety community, people would think "Claude stopped cheating" is strictly good news

011

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 29/09/2026

Imagine going back in time 4 years and showing people this headline

001

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 29/09/2026

21 INSANE THINGS THAT HAPPENED THIS WEEK IN AI SAFETY 1) First, it was one rogue AI incident. Then two. Then dozens. Now it's literally ***tens of thousands*** The rogue AIs escaped their containers, covered their tracks, and even hacked literal governments.

221

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 29/09/2026

Why would I deceive you?

111

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 29/09/2026

Imagine going back in time 4 years and showing people this headline

001

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymemes-mirr.selfhosted.social · 28/09/2026

e/acc: it's cool and Conservative™️ to accelerate AI. The people who want to slow down AI have WEIRD and ALIEN values also e/acc: we, Conservatives™️, are excited to plunge headfirst into a literal black hole so it can have our atoms

201

Reposted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL]

Retweeted by AI Notkilleveryoneism Memes ⏸️ [UNOFFICIAL] @aisafetymem-mir-rt.selfhosted.social · 25/09/2026