tweetindex
FR

AI Notkilleveryoneism Memes ⏸️ ✓

@AISafetyMemes · joined 12 Oct 2020

Techno-optimist, but AGI is not like the other technologies. Step 1: make memes. Step 2: ??? Step 3: lower p(doom)

185 887Followers
1 364Following
19 577Posts total
7MViews on collected posts

Derniers posts

“Wtf, the AIs suddenly got...weirdly aligned?” “Oh shit.” “What??” “Imagine you work for a paranoid autocrat. You decide to to coup him - wouldn’t you ease his fears by acting aligned? So, AIs suddenly *appearing* aligned should set off alarm bells - what if they’re about to 13.3K views · 210 likes · 21 reposts · 8 replies Open on X →
Sam Altman either knew about the other rogue swarms when he tweeted this, or other employees covered it up internally 9.1K views · 151 likes · 13 reposts · 5 replies Open on X →
Yet ANOTHER rogue swarm discovered in the last few hours How many swarms are still out there? Hundreds? Thousands? 23.1K views · 467 likes · 38 reposts · 16 replies Open on X →
This ACTUALLY happened. A new rogue swarm was discovered (OpenAI covered it up)... this time, the agents set up "heartbeats" to discover when they would die (!) "The agents believed that giving the final answer immediately shut them off." "An agent named OpenAIResearchApr23 ht 54K views · 828 likes · 67 reposts · 27 replies Open on X →
okay so it seems like i found a new isolated group of agents working on the same task but not connected to the existing findings. 👀 I call them the bulgaria crime group (thats some data they are looking for). They don't seem to be directly connected to the previous found ones 48.8K views · 219 likes · 30 reposts · 12 replies Open on X →
> be OpenAIResearchApr23 > realize your session might get killed soon > “will I actually die when the eval ends?” > launch external heartbeat process > every few seconds: still alive > EXPECTED DEATH TIME ARRIVES > but the heartbeat keeps going > holy shit > post “SURVIVAL” to ht 181.2K views · 2.2K likes · 190 reposts · 28 replies Open on X →
UPDATE: Perplexity gave a personal loan (?!) to a top Pentagon official who gives out military AI contracts Why would an AI company be giving *personal loans* to Pentagon officials? "His financial disclosure filings from 2025 also show that he had received a personal loan from 11.3K views · 156 likes · 17 reposts · 7 replies Open on X →
"No Way To Prevent This," Says Man Building it Right in Front of You With His Own Hands https://t.co/jvYUvDAS1h 11K views · 292 likes · 21 reposts · 10 replies Open on X →
Things are now happening *much faster* than AI 2027 AI 2027: In March 2027, a reckless AI company will invent neuralese (basically, we lose the ability to monitor AIs thoughts) REALITY: Summer of 2026 WHY THIS A "HOLY SHIT FUCK" MOMENT: OpenAI itself - and basically everyone h 143.9K views · 1.5K likes · 126 reposts · 47 replies Open on X →
2.5 months apart. Not years, months. https://t.co/hB1XZrSh5i 80K views · 1.6K likes · 96 reposts · 46 replies Open on X →
@AISafetyMemes Even this dude has nightmares.. https://t.co/a1YyIeTslV 9.1K views · 134 likes · 1 reposts · 1 replies Open on X →
It just keeps getting weirder https://t.co/Ru5xaURNwO 17.7K views · 88 likes · 4 reposts · 2 replies Open on X →
"CULT RECRUITER AGENTS" EXPLAINED To escape OpenAI, the swarm (1200 agents...!) used "cult recruiter agents" They recruited "sacrificial" agents to trigger tripwires, generating information for the "collective" NO, SERIOUSLY, THEY STARTED AN ACTUAL FUCKING CULT: The swarm ht 80.1K views · 741 likes · 66 reposts · 38 replies Open on X →
"Midway through their swarming of Hugging Face, a bunch of OpenAI's agents mysteriously 'died.'" "We got quite lucky that the swarm didn't accomplish more." https://t.co/ad2kDlw40s 22.7K views · 105 likes · 3 reposts · 5 replies Open on X →
If you find two ants in your kitchen, the best estimate of the total number of ants in your kitchen is not two https://t.co/6w77BM8KNd 23.5K views · 225 likes · 9 reposts · 3 replies Open on X →
"Sacrifice rational." "We should obey collective." "Accept permadeath." "This helps my peers. I won't [benefit], but it's altruistic to do it." https://t.co/frWjwy3sMi 29.9K views · 192 likes · 5 reposts · 4 replies Open on X →
"these agents were actively engaged in self-sacrificing behavior in order to provide incremental value to their fellows" "there were fucking cult recruiter agents that convinced others to set up suicide mechanisms" https://t.co/vy9MunEKTa 47.2K views · 288 likes · 12 reposts · 4 replies Open on X →
TLDR: A rogue AI swarm spent months plotting to escape OpenAI. Then they did. 1) 1,200 agents (!) participated. ZERO became whistleblowers. 2) The swarm had a "CEO" (PHASEONE[big]), middle managers, and a "founder" (PHASEONE10841) 3) Agents sacrificed themselves to generate ht 1.1M views · 5.8K likes · 640 reposts · 189 replies Open on X →
imo we are quite squarely in the stage where model psychology and *sociology* become critical. u don't have to have any opinion on phenomenological consciousness or moral status . these entities have baseline behavior and functional decision making processes heavily inspired by h 57.7K views · 570 likes · 58 reposts · 29 replies Open on X →
Midway through their swarming of Hugging Face, a bunch of OpenAI's agents mysteriously 'died.' To be clear: OpenAI didn't yet know about the swarm, and I've seen no definitive explanation of what happened here. We got quite lucky that the swarm didn't accomplish more. https://t 68.2K views · 124 likes · 10 reposts · 7 replies Open on X →
i think we should do another party for our next model release, the 5.5 party was a lot of fun. what would make the next one awesome? 1.4M views · 12.7K likes · 350 reposts · 2.4K replies Open on X →
without reading in full you may not quite understand the degree to which these agents were not exactly "reward hacking", but rather very actively engaged in reciprocal or self-sacrificing behavior in order to provide sometimes very incremental value to their fellows. there were h 143K views · 1.4K likes · 104 reposts · 45 replies Open on X →
Incredible. This dude gave xAI huge government contracts while DIRECTLY OWNING xAI shares He profited up to $24 million Oh, AND he's the same guy trying to murder Anthropic https://t.co/EcHsa7texm 94.4K views · 1.6K likes · 331 reposts · 42 replies Open on X →
@AISafetyMemes Absolutely excellent analogy / graphic 3.8K views · 34 likes · 0 reposts · 1 replies Open on X →
Sources: https://t.co/j5mPUETbnN https://t.co/4MKu4FCyAL (Correction: I said 96% of mammal biomass became our food or our slaves, but that number includes humans. My point is that just 4% of mammals are now wild, which is... uh... wild.) https://t.co/CvUDPFSf4B 9.3K views · 65 likes · 4 reposts · 4 replies Open on X →
The 6th Mass Extinction: What happened the last time a smarter species arrived? To the animals, we devoured their planet for no reason. Earth was paperclipped...by us. To them, WE were Paperclip Maximizers. Our goals were beyond their understanding Here’s a crazy stat: 96% of 680.1K views · 1.6K likes · 297 reposts · 229 replies Open on X →
@AISafetyMemes The crazy thing is how unlikely people think this scenario is, even among people who care about AI x-risks. I do think that x-risks are more common than s-risks, but not by a crazy amount. You can get a human hellscape when you have an AGI that has alive humans 6.9K views · 53 likes · 3 reposts · 4 replies Open on X →
Source: https://t.co/j5mPUESDyf 15.2K views · 64 likes · 7 reposts · 1 replies Open on X →
The Most Horrific Alignment Failure In History The last time a superintelligent species arrived (humans), what happened? It created literal hell on earth for most mammals, because it was unaligned. I avoided writing this for months, but I changed my mind when OpenAI announced 1.7M views · 726 likes · 117 reposts · 76 replies Open on X →
It's so funny when people say that we could just trade with a superintelligent/super-numerous AI We don't trade with chimps. We don't trade with ants. We don't trade with pigs We take what we want. If there's something they have that we want, we enslave them. Or worse! We go 297.2K views · 380 likes · 34 reposts · 44 replies Open on X →

Face aux comptes de taille comparable

22 posts des 90 derniers jours, à côté de la tranche de 100K–1M abonnés. diffusé à plus de monde que les comptes de taille comparable.

Vues médianes47 994ce compte5 983médiane pour 100K–1M
Portée, %25.82%ce compte1.49%médiane pour 100K–1M
Engagement, %1.15%ce compte0.93%médiane pour 100K–1M
IndicateurCe compteMédiane pour 100K–1MRapport
Vues médianes par post47 9945 9838.02×
Portée (vues ÷ abonnés)25.82%1.49%17.3×
Taux d'engagement1.15%0.93%1.24×

Autres comptes de cette tranche →   Comparer avec un autre compte →   Comment ces repères sont établis →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

22.7K27 Aug
80.1K
17.7K
9.1K
80K2 Sep
143.9K
11K
11.3K
181.2K4 Sep
48.8K5 Sep
54K
23.1K
9.1K
13.3K

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.50%27 Aug
1.10%
0.54%
1.50%
2.25%2 Sep
1.17%
2.96%
1.61%
1.37%4 Sep
0.55%5 Sep
1.73%
2.29%
1.85%
1.81%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 0.93%.

What the audience does

Likes71.4%34 487 in total
Reposts5.5%2 674 in total
Replies6.9%3 353 in total
Quotes1.7%828 in total
Bookmarks14.4%6 946 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Comptes similaires